From e216094e2192c05ddbd0988458eb8c0012e7baf8 Mon Sep 17 00:00:00 2001 From: Vicent Marti Date: Tue, 2 Sep 2014 01:10:54 +0200 Subject: lol --- Makefile | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'Makefile') diff --git a/Makefile b/Makefile index 55b6645..cb5938d 100644 --- a/Makefile +++ b/Makefile @@ -1,5 +1,5 @@ -CFLAGS=-g -O3 -Wall -Wextra -std=c99 -Isrc $(OPTFLAGS) -LDFLAGS=-g -O3 -Wall -Werror +CFLAGS=-ggdb3 -O0 -Wall -Wextra -std=c99 -Isrc $(OPTFLAGS) +LDFLAGS=-ggdb3 -O0 -Wall -Werror SRCDIR=src DATADIR=data @@ -41,13 +41,13 @@ testjs: spec.txt benchjs: node js/bench.js ${BENCHINP} -$(PROG): $(SRCDIR)/main.c $(SRCDIR)/inlines.o $(SRCDIR)/blocks.o $(SRCDIR)/detab.o $(SRCDIR)/bstrlib.o $(SRCDIR)/scanners.o $(SRCDIR)/print.o $(SRCDIR)/html.o $(SRCDIR)/utf8.o +$(PROG): $(SRCDIR)/main.c $(SRCDIR)/inlines.o $(SRCDIR)/buffer.o $(SRCDIR)/blocks.o $(SRCDIR)/scanners.c $(SRCDIR)/print.o $(SRCDIR)/html.o $(SRCDIR)/utf8.o $(CC) $(LDFLAGS) -o $@ $^ $(SRCDIR)/scanners.c: $(SRCDIR)/scanners.re re2c --case-insensitive -bis $< > $@ || (rm $@ && false) -$(SRCDIR)/case_fold_switch.c: $(DATADIR)/CaseFolding-3.2.0.txt +$(SRCDIR)/case_fold_switch.inc $(DATADIR)/CaseFolding-3.2.0.txt perl mkcasefold.pl < $< > $@ .PHONY: leakcheck clean fuzztest dingus upload @@ -58,6 +58,9 @@ dingus: leakcheck: $(PROG) cat oldtests/*/*.markdown | valgrind --leak-check=full --dsymutil=yes $(PROG) +operf: $(PROG) + operf $(PROG) /dev/null + fuzztest: for i in `seq 1 10`; do \ time cat /dev/urandom | head -c 100000 | iconv -f latin1 -t utf-8 | $(PROG) >/dev/null; done @@ -69,7 +72,7 @@ update-site: spec.html narrative.html (cd _site ; git pull ; git commit -a -m "Updated site for latest spec, narrative, js" ; git push; cd ..) clean: - -rm test $(SRCDIR)/*.o $(SRCDIR)/scanners.c - -rm -r *.dSYM - -rm README.html - -rm spec.md fuzz.txt spec.html + -rm -f test $(SRCDIR)/*.o $(SRCDIR)/scanners.c + -rm -rf *.dSYM + -rm -f README.html + -rm -f spec.md fuzz.txt spec.html -- cgit v1.2.3 From 582674e662d1f8757350c51486a5e0a837195e15 Mon Sep 17 00:00:00 2001 From: Vicent Marti Date: Tue, 2 Sep 2014 13:18:04 +0200 Subject: ffffix --- Makefile | 11 ++- src/blocks.c | 58 +++++++---- src/buffer.c | 69 +++++-------- src/buffer.h | 19 ++-- src/html.c | 276 ---------------------------------------------------- src/inlines.c | 4 +- src/main.c | 142 ++++++++++++--------------- src/print.c | 307 ++++++++++++++++++++++++++++++---------------------------- src/stmd.h | 13 +-- src/utf8.c | 6 +- src/utf8.h | 6 -- 11 files changed, 304 insertions(+), 607 deletions(-) delete mode 100644 src/html.c delete mode 100644 src/utf8.h (limited to 'Makefile') diff --git a/Makefile b/Makefile index cb5938d..d14a928 100644 --- a/Makefile +++ b/Makefile @@ -6,7 +6,7 @@ DATADIR=data PROG=./stmd .PHONY: all oldtests test spec benchjs testjs -all: $(SRCDIR)/case_fold_switch.c $(PROG) +all: $(SRCDIR)/case_fold_switch.inc $(PROG) README.html: README.md template.html pandoc --template template.html -S -s -t html5 -o $@ $< @@ -41,13 +41,16 @@ testjs: spec.txt benchjs: node js/bench.js ${BENCHINP} -$(PROG): $(SRCDIR)/main.c $(SRCDIR)/inlines.o $(SRCDIR)/buffer.o $(SRCDIR)/blocks.o $(SRCDIR)/scanners.c $(SRCDIR)/print.o $(SRCDIR)/html.o $(SRCDIR)/utf8.o +HTML_OBJ=$(SRCDIR)/html/html.o $(SRCDIR)/html/houdini_href_e.o $(SRCDIR)/html/houdini_html_e.o +STMD_OBJ=$(SRCDIR)/inlines.o $(SRCDIR)/buffer.o $(SRCDIR)/blocks.o $(SRCDIR)/scanners.c $(SRCDIR)/print.o $(SRCDIR)/utf8.o + +$(PROG): $(SRCDIR)/main.c $(HTML_OBJ) $(STMD_OBJ) $(CC) $(LDFLAGS) -o $@ $^ $(SRCDIR)/scanners.c: $(SRCDIR)/scanners.re re2c --case-insensitive -bis $< > $@ || (rm $@ && false) -$(SRCDIR)/case_fold_switch.inc $(DATADIR)/CaseFolding-3.2.0.txt +$(SRCDIR)/case_fold_switch.inc: $(DATADIR)/CaseFolding-3.2.0.txt perl mkcasefold.pl < $< > $@ .PHONY: leakcheck clean fuzztest dingus upload @@ -72,7 +75,7 @@ update-site: spec.html narrative.html (cd _site ; git pull ; git commit -a -m "Updated site for latest spec, narrative, js" ; git push; cd ..) clean: - -rm -f test $(SRCDIR)/*.o $(SRCDIR)/scanners.c + -rm -f test $(SRCDIR)/*.o $(SRCDIR)/scanners.c $(SRCDIR)/html/*.o -rm -rf *.dSYM -rm -f README.html -rm -f spec.md fuzz.txt spec.html diff --git a/src/blocks.c b/src/blocks.c index eabac03..71dc830 100644 --- a/src/blocks.c +++ b/src/blocks.c @@ -3,11 +3,12 @@ #include #include #include -#include "bstrlib.h" + #include "stmd.h" -#include "uthash.h" -#include "debug.h" #include "scanners.h" +#include "uthash.h" + +static void finalize(block* b, int line_number); static block* make_block(int tag, int start_line, int start_column) { @@ -140,7 +141,7 @@ static int break_out_of_lists(block ** bptr, int line_number) } -extern void finalize(block* b, int line_number) +static void finalize(block* b, int line_number) { int firstlinelen; int pos; @@ -364,7 +365,7 @@ static int lists_match(struct ListData list_data, list_data.bullet_char == item_data.bullet_char); } -static void expand_tabs(gh_buf *ob, const char *line, size_t size) +static void expand_tabs(gh_buf *ob, const unsigned char *line, size_t size) { size_t i = 0, tab = 0; @@ -389,13 +390,43 @@ static void expand_tabs(gh_buf *ob, const char *line, size_t size) } } -extern block *stmd_parse_document(const char *buffer, size_t len) +static block *finalize_parsing(block *document, int linenum) { - gh_buf line = GH_BUF_INIT; + while (document != document->top) { + finalize(document, linenum); + document = document->parent; + } + + finalize(document, linenum); + process_inlines(document, document->attributes.refmap); + + return document; +} +extern block *stmd_parse_file(FILE *f) +{ + gh_buf line = GH_BUF_INIT; + unsigned char buffer[4096]; + int linenum = 1; block *document = make_document(); + + while (fgets((char *)buffer, sizeof(buffer), f)) { + expand_tabs(&line, buffer, strlen(buffer)); + incorporate_line(&line, linenum, &document); + gh_buf_clear(&line); + linenum++; + } + + gh_buf_free(&line); + return finalize_document(document, linenum); +} + +extern block *stmd_parse_document(const unsigned char *buffer, size_t len) +{ + gh_buf line = GH_BUF_INIT; int linenum = 1; - const char *end = buffer + len; + const unsigned char *end = buffer + len; + block *document = make_document(); while (buffer < end) { const char *eol = memchr(buffer, '\n', end - buffer); @@ -414,16 +445,7 @@ extern block *stmd_parse_document(const char *buffer, size_t len) } gh_buf_free(&line); - - while (document != document->top) { - finalize(document, linenum); - document = document->parent; - } - - finalize(document, linenum); - process_inlines(document, document->attributes.refmap); - - return document; + return finalize_document(document, linenum); } // Process one line at a time, modifying a block. diff --git a/src/buffer.c b/src/buffer.c index b81e7fa..17dc864 100644 --- a/src/buffer.c +++ b/src/buffer.c @@ -31,10 +31,10 @@ void gh_buf_init(gh_buf *buf, int initial_size) int gh_buf_try_grow(gh_buf *buf, int target_size, bool mark_oom) { - char *new_ptr; - size_t new_size; + unsigned char *new_ptr; + int new_size; - if (buf->ptr == gh_buf__oom || buf->asize < 0) + if (buf->ptr == gh_buf__oom) return -1; if (target_size <= buf->asize) @@ -79,7 +79,7 @@ void gh_buf_free(gh_buf *buf) { if (!buf) return; - if (buf->asize > 0 && buf->ptr != gh_buf__initbuf && buf->ptr != gh_buf__oom) + if (buf->ptr != gh_buf__initbuf && buf->ptr != gh_buf__oom) free(buf->ptr); gh_buf_init(buf, 0); @@ -91,14 +91,9 @@ void gh_buf_clear(gh_buf *buf) if (buf->asize > 0) buf->ptr[0] = '\0'; - - if (buf->asize < 0) { - buf->ptr = gh_buf__initbuf; - buf->asize = 0; - } } -int gh_buf_set(gh_buf *buf, const char *data, int len) +int gh_buf_set(gh_buf *buf, const unsigned char *data, int len) { if (len == 0 || data == NULL) { gh_buf_clear(buf); @@ -115,10 +110,12 @@ int gh_buf_set(gh_buf *buf, const char *data, int len) int gh_buf_sets(gh_buf *buf, const char *string) { - return gh_buf_set(buf, string, string ? strlen(string) : 0); + return gh_buf_set(buf, + (const unsigned char *)string, + string ? strlen(string) : 0); } -int gh_buf_putc(gh_buf *buf, char c) +int gh_buf_putc(gh_buf *buf, int c) { ENSURE_SIZE(buf, buf->size + 2); buf->ptr[buf->size++] = c; @@ -126,7 +123,7 @@ int gh_buf_putc(gh_buf *buf, char c) return 0; } -int gh_buf_put(gh_buf *buf, const char *data, int len) +int gh_buf_put(gh_buf *buf, const unsigned char *data, int len) { ENSURE_SIZE(buf, buf->size + len + 1); memmove(buf->ptr + buf->size, data, len); @@ -137,8 +134,7 @@ int gh_buf_put(gh_buf *buf, const char *data, int len) int gh_buf_puts(gh_buf *buf, const char *string) { - assert(string); - return gh_buf_put(buf, string, strlen(string)); + return gh_buf_put(buf, (const unsigned char *)string, strlen(string)); } int gh_buf_vprintf(gh_buf *buf, const char *format, va_list ap) @@ -153,7 +149,7 @@ int gh_buf_vprintf(gh_buf *buf, const char *format, va_list ap) va_copy(args, ap); len = vsnprintf( - buf->ptr + buf->size, + (char *)buf->ptr + buf->size, buf->asize - buf->size, format, args ); @@ -187,9 +183,9 @@ int gh_buf_printf(gh_buf *buf, const char *format, ...) return r; } -void gh_buf_copy_cstr(char *data, size_t datasize, const gh_buf *buf) +void gh_buf_copy_cstr(char *data, int datasize, const gh_buf *buf) { - size_t copylen; + int copylen; assert(data && datasize && buf); @@ -212,9 +208,9 @@ void gh_buf_swap(gh_buf *buf_a, gh_buf *buf_b) *buf_b = t; } -char *gh_buf_detach(gh_buf *buf) +unsigned char *gh_buf_detach(gh_buf *buf) { - char *data = buf->ptr; + unsigned char *data = buf->ptr; if (buf->asize == 0 || buf->ptr == gh_buf__oom) return NULL; @@ -224,13 +220,13 @@ char *gh_buf_detach(gh_buf *buf) return data; } -void gh_buf_attach(gh_buf *buf, char *ptr, int asize) +void gh_buf_attach(gh_buf *buf, unsigned char *ptr, int asize) { gh_buf_free(buf); if (ptr) { buf->ptr = ptr; - buf->size = strlen(ptr); + buf->size = strlen((char *)ptr); if (asize) buf->asize = (asize < buf->size) ? buf->size + 1 : asize; else /* pass 0 to fall back on strlen + 1 */ @@ -249,11 +245,11 @@ int gh_buf_cmp(const gh_buf *a, const gh_buf *b) int gh_buf_strchr(const gh_buf *buf, int c, int pos) { - const char *p = memchr(buf->ptr + pos, c, buf->size - pos); - if (!p) - return -1; + const char *p = memchr(buf->ptr + pos, c, buf->size - pos); + if (!p) + return -1; - return (int)(p - p->ptr); + return (int)(p - buf->ptr); } int gh_buf_strrchr(const gh_buf *buf, int c, int pos) @@ -270,36 +266,21 @@ int gh_buf_strrchr(const gh_buf *buf, int c, int pos) void gh_buf_truncate(gh_buf *buf, size_t len) { - assert(buf->asize >= 0); - if (len < buf->size) { buf->size = len; buf->ptr[buf->size] = '\0'; } } -void gh_buf_ltruncate(gh_buf *buf, size_t len) -{ - assert(buf->asize >= 0); - - if (len && len < buf->size) { - memmove(buf->ptr, buf->ptr + len, buf->size - len); - buf->size -= len; - buf->ptr[buf->size] = '\0'; - } -} - void gh_buf_trim(gh_buf *buf) { - size_t i = 0; - - assert(buf->asize >= 0); - - /* ltrim */ + /* TODO: leading whitespace? */ + /* while (i < buf->size && isspace(buf->ptr[i])) i++; gh_buf_truncate(buf, i); + */ /* rtrim */ while (buf->size > 0) { diff --git a/src/buffer.h b/src/buffer.h index 2581ee3..422ef02 100644 --- a/src/buffer.h +++ b/src/buffer.h @@ -24,13 +24,6 @@ extern unsigned char gh_buf__oom[]; */ extern void gh_buf_init(gh_buf *buf, int initial_size); -static inline void gh_buf_static(gh_buf *buf, unsigned char *source) -{ - buf->ptr = source; - buf->size = strlen(source); - buf->asize = -1; -} - /** * Attempt to grow the buffer to hold at least `target_size` bytes. * @@ -81,13 +74,13 @@ static inline size_t gh_buf_len(const gh_buf *buf) extern int gh_buf_cmp(const gh_buf *a, const gh_buf *b); -extern void gh_buf_attach(gh_buf *buf, char *ptr, int asize); -extern char *gh_buf_detach(gh_buf *buf); +extern void gh_buf_attach(gh_buf *buf, unsigned char *ptr, int asize); +extern unsigned char *gh_buf_detach(gh_buf *buf); extern void gh_buf_copy_cstr(char *data, int datasize, const gh_buf *buf); static inline const char *gh_buf_cstr(const gh_buf *buf) { - return buf->ptr; + return (char *)buf->ptr; } #define gh_buf_at(buf, n) ((buf)->ptr[n]) @@ -100,10 +93,10 @@ static inline const char *gh_buf_cstr(const gh_buf *buf) * return code of these functions and call them in a series then just call * gh_buf_oom at the end. */ -extern int gh_buf_set(gh_buf *buf, const char *data, int len); +extern int gh_buf_set(gh_buf *buf, const unsigned char *data, int len); extern int gh_buf_sets(gh_buf *buf, const char *string); -extern int gh_buf_putc(gh_buf *buf, char c); -extern int gh_buf_put(gh_buf *buf, const char *data, int len); +extern int gh_buf_putc(gh_buf *buf, int c); +extern int gh_buf_put(gh_buf *buf, const unsigned char *data, int len); extern int gh_buf_puts(gh_buf *buf, const char *string); extern int gh_buf_printf(gh_buf *buf, const char *format, ...) __attribute__((format (printf, 2, 3))); diff --git a/src/html.c b/src/html.c deleted file mode 100644 index aeec5f1..0000000 --- a/src/html.c +++ /dev/null @@ -1,276 +0,0 @@ -#include -#include -#include -#include "bstrlib.h" -#include "stmd.h" -#include "debug.h" -#include "scanners.h" - -// Functions to convert block and inline lists to HTML strings. - -// Escape special characters in HTML. More efficient than -// three calls to bfindreplace. If preserve_entities is set, -// existing entities are left alone. -static bstring escape_html(bstring inp, bool preserve_entities) -{ - int pos = 0; - int match; - char c; - bstring escapable = blk2bstr("&<>\"", 4); - bstring ent; - bstring s = bstrcpy(inp); - while ((pos = binchr(s, pos, escapable)) != BSTR_ERR) { - c = bchar(s,pos); - switch (c) { - case '<': - bdelete(s, pos, 1); - ent = blk2bstr("<", 4); - binsert(s, pos, ent, ' '); - bdestroy(ent); - pos += 4; - break; - case '>': - bdelete(s, pos, 1); - ent = blk2bstr(">", 4); - binsert(s, pos, ent, ' '); - bdestroy(ent); - pos += 4; - break; - case '&': - if (preserve_entities && (match = scan_entity(s, pos))) { - pos += match; - } else { - bdelete(s, pos, 1); - ent = blk2bstr("&", 5); - binsert(s, pos, ent, ' '); - bdestroy(ent); - pos += 5; - } - break; - case '"': - bdelete(s, pos, 1); - ent = blk2bstr(""", 6); - binsert(s, pos, ent, ' '); - bdestroy(ent); - pos += 6; - break; - default: - bdelete(s, pos, 1); - log_err("unexpected character %02x", c); - } - } - bdestroy(escapable); - return s; -} - -static inline void cr(bstring buffer) -{ - int c = bchar(buffer, blength(buffer) - 1); - if (c != '\n' && c) { - bconchar(buffer, '\n'); - } -} - -// Convert a block list to HTML. Returns 0 on success, and sets result. -extern int blocks_to_html(block* b, bstring* result, bool tight) -{ - bstring contents = NULL; - bstring escaped, escaped2; - struct bstrList * info_words; - struct ListData * data; - bstring mbstart; - bstring html = blk2bstr("", 0); - - while(b != NULL) { - switch(b->tag) { - case document: - check(blocks_to_html(b->children, &contents, false) == 0, - "error converting blocks to html"); - bformata(html, "%s", contents->data); - bdestroy(contents); - break; - case paragraph: - check(inlines_to_html(b->inline_content, &contents) == 0, - "error converting inlines to html"); - if (tight) { - bformata(html, "%s", contents->data); - } else { - cr(html); - bformata(html, "

%s

", contents->data); - cr(html); - } - bdestroy(contents); - break; - case block_quote: - check(blocks_to_html(b->children, &contents, false) == 0, - "error converting blocks to html"); - cr(html); - bformata(html, "
\n%s
", contents->data); - cr(html); - bdestroy(contents); - break; - case list_item: - check(blocks_to_html(b->children, &contents, tight) == 0, - "error converting blocks to html"); - brtrimws(contents); - cr(html); - bformata(html, "
  • %s
    • ", contents->data); - cr(html); - bdestroy(contents); - break; - case list: - // make sure a list starts at the beginning of the line: - cr(html); - data = &(b->attributes.list_data); - check(blocks_to_html(b->children, &contents, data->tight) == 0, - "error converting blocks to html"); - mbstart = bformat(" start=\"%d\"", data->start); - bformata(html, "<%s%s>\n%s", - data->list_type == bullet ? "ul" : "ol", - data->start == 1 ? "" : (char*) mbstart->data, - contents->data, - data->list_type == bullet ? "ul" : "ol"); - cr(html); - bdestroy(contents); - bdestroy(mbstart); - break; - case atx_header: - case setext_header: - check(inlines_to_html(b->inline_content, &contents) == 0, - "error converting inlines to html"); - cr(html); - bformata(html, "%s", - b->attributes.header_level, - contents->data, - b->attributes.header_level); - cr(html); - bdestroy(contents); - break; - case indented_code: - escaped = escape_html(b->string_content, false); - cr(html); - bformata(html, "
    %s
    ", escaped->data); - cr(html); - bdestroy(escaped); - break; - case fenced_code: - escaped = escape_html(b->string_content, false); - cr(html); - bformata(html, "
    attributes.fenced_code_data.info) > 0) {
-        escaped2 = escape_html(b->attributes.fenced_code_data.info, true);
-        info_words = bsplit(escaped2, ' ');
-        bformata(html, " class=\"language-%s\"", info_words->entry[0]->data);
-        bdestroy(escaped2);
-        bstrListDestroy(info_words);
-      }
-      bformata(html, ">%s
    ", escaped->data); - cr(html); - bdestroy(escaped); - break; - case html_block: - bformata(html, "%s", b->string_content->data); - break; - case hrule: - bformata(html, "
    "); - cr(html); - break; - case reference_def: - break; - default: - log_warn("block type %d not implemented\n", b->tag); - break; - } - b = b->next; - } - *result = html; - return 0; - error: - return -1; -} - -// Convert an inline list to HTML. Returns 0 on success, and sets result. -extern int inlines_to_html(inl* ils, bstring* result) -{ - bstring contents = NULL; - bstring html = blk2bstr("", 0); - bstring mbtitle, escaped, escaped2; - - while(ils != NULL) { - switch(ils->tag) { - case str: - escaped = escape_html(ils->content.literal, false); - bformata(html, "%s", escaped->data); - bdestroy(escaped); - break; - case linebreak: - bformata(html, "
    \n"); - break; - case softbreak: - bformata(html, "\n"); - break; - case code: - escaped = escape_html(ils->content.literal, false); - bformata(html, "%s", escaped->data); - bdestroy(escaped); - break; - case raw_html: - case entity: - bformata(html, "%s", ils->content.literal->data); - break; - case link: - check(inlines_to_html(ils->content.inlines, &contents) == 0, - "error converting inlines to html"); - if (blength(ils->content.linkable.title) > 0) { - escaped = escape_html(ils->content.linkable.title, true); - mbtitle = bformat(" title=\"%s\"", escaped->data); - bdestroy(escaped); - } else { - mbtitle = blk2bstr("",0); - } - escaped = escape_html(ils->content.linkable.url, true); - bformata(html, "%s", - escaped->data, - mbtitle->data, - contents->data); - bdestroy(escaped); - bdestroy(mbtitle); - bdestroy(contents); - break; - case image: - check(inlines_to_html(ils->content.inlines, &contents) == 0, - "error converting inlines to html"); - escaped = escape_html(ils->content.linkable.url, true); - escaped2 = escape_html(contents, false); - bdestroy(contents); - bformata(html, "\"%s\"",data, escaped2->data); - bdestroy(escaped); - bdestroy(escaped2); - if (blength(ils->content.linkable.title) > 0) { - escaped = escape_html(ils->content.linkable.title, true); - bformata(html, " title=\"%s\"", escaped->data); - bdestroy(escaped); - } - bformata(html, " />"); - break; - case strong: - check(inlines_to_html(ils->content.inlines, &contents) == 0, - "error converting inlines to html"); - bformata(html, "%s", contents->data); - bdestroy(contents); - break; - case emph: - check(inlines_to_html(ils->content.inlines, &contents) == 0, - "error converting inlines to html"); - bformata(html, "%s", contents->data); - bdestroy(contents); - break; - } - ils = ils->next; - } - *result = html; - return 0; - error: - return -1; -} diff --git a/src/inlines.c b/src/inlines.c index 4ff45ad..82c7219 100644 --- a/src/inlines.c +++ b/src/inlines.c @@ -6,9 +6,7 @@ #include "stmd.h" #include "uthash.h" -#include "debug.h" #include "scanners.h" -#include "utf8.h" typedef struct Subject { const gh_buf *buffer; @@ -119,7 +117,7 @@ inline static inl* make_linkable(int t, inl* label, chunk url, chunk title) e->tag = t; e->content.linkable.label = label; e->content.linkable.url = chunk_to_cstr(&url); - e->content.linkable.title = chunk_to_cstr(&title); + e->content.linkable.title = url.len ? chunk_to_cstr(&title) : NULL; e->next = NULL; return e; } diff --git a/src/main.c b/src/main.c index 9e0a3c8..e1abedc 100644 --- a/src/main.c +++ b/src/main.c @@ -1,99 +1,77 @@ #include #include -#include "bstrlib.h" +#include #include "stmd.h" #include "debug.h" void print_usage() { - printf("Usage: stmd [FILE*]\n"); - printf("Options: --help, -h Print usage information\n"); - printf(" --ast Print AST instead of HTML\n"); - printf(" --version Print version\n"); + printf("Usage: stmd [FILE*]\n"); + printf("Options: --help, -h Print usage information\n"); + printf(" --ast Print AST instead of HTML\n"); + printf(" --version Print version\n"); } -int main(int argc, char *argv[]) { - int i; - bool ast = false; - int g = 0; - int numfps = 0; - int files[argc]; +static void print_document(block *document, bool ast) +{ + gh_buf html = GH_BUF_INIT; + + if (ast) { + print_blocks(document, 0); + } else { + blocks_to_html(&html, document, false); + printf("%s", html.ptr); + gh_buf_free(&html); + } +} - for (i=1; i < argc; i++) { - if (strcmp(argv[i], "--version") == 0) { - printf("stmd %s", VERSION); - printf(" - CommonMark converter (c) 2014 John MacFarlane\n"); - exit(0); - } else if ((strcmp(argv[i], "--help") == 0) || - (strcmp(argv[i], "-h") == 0)) { - print_usage(); - exit(0); - } else if (strcmp(argv[i], "--ast") == 0) { - ast = true; - } else if (*argv[i] == '-') { - print_usage(); - exit(1); - } else { // treat as file argument - files[g] = i; - g++; - } - } +int main(int argc, char *argv[]) +{ + int i, numfps = 0; + bool ast = false; + int files[argc]; + block *document = NULL; - numfps = g; - bstring s = NULL; - bstring html; - g = 0; - block * cur = make_document(); - int linenum = 1; - extern int errno; - FILE * fp = NULL; + for (i = 1; i < argc; i++) { + if (strcmp(argv[i], "--version") == 0) { + printf("stmd %s", VERSION); + printf(" - CommonMark converter (c) 2014 John MacFarlane\n"); + exit(0); + } else if ((strcmp(argv[i], "--help") == 0) || + (strcmp(argv[i], "-h") == 0)) { + print_usage(); + exit(0); + } else if (strcmp(argv[i], "--ast") == 0) { + ast = true; + } else if (*argv[i] == '-') { + print_usage(); + exit(1); + } else { // treat as file argument + files[numfps++] = i; + } + } - if (numfps == 0) { - // read from stdin - while ((s = bgets((bNgetc) fgetc, stdin, '\n'))) { - check(incorporate_line(s, linenum, &cur) == 0, - "error incorporating line %d", linenum); - bdestroy(s); - linenum++; - } - } else { - // iterate over input file pointers - for (g=0; g < numfps; g++) { + if (numfps == 0) { + document = stmd_parse_file(stdin); + print_document(document, ast); + free_blocks(document); + } else { + for (i = 0; i < numfps; i++) { + FILE *fp = fopen(argv[files[i]], "r"); - fp = fopen(argv[files[g]], "r"); - if (fp == NULL) { - fprintf(stderr, "Error opening file %s: %s\n", - argv[files[g]], strerror(errno)); - exit(1); - } + if (fp == NULL) { + fprintf(stderr, "Error opening file %s: %s\n", + argv[files[i]], strerror(errno)); + exit(1); + } - while ((s = bgets((bNgetc) fgetc, fp, '\n'))) { - check(incorporate_line(s, linenum, &cur) == 0, - "error incorporating line %d", linenum); - bdestroy(s); - linenum++; - } - fclose(fp); - } - } + document = stmd_parse_file(fp); + print_document(document, ast); + free_blocks(document); + fclose(fp); + } + } - while (cur != cur->top) { - finalize(cur, linenum); - cur = cur->parent; - } - check(cur == cur->top, "problems finalizing open containers"); - finalize(cur, linenum); - process_inlines(cur, cur->attributes.refmap); - if (ast) { - print_blocks(cur, 0); - } else { - check(blocks_to_html(cur, &html, false) == 0, "could not format as HTML"); - // printf("%s", html->data); - bdestroy(html); - } - free_blocks(cur); - return 0; -error: - return -1; + return 0; } diff --git a/src/print.c b/src/print.c index a924870..3ebde16 100644 --- a/src/print.c +++ b/src/print.c @@ -1,168 +1,175 @@ #include #include -#include "bstrlib.h" +#include #include "stmd.h" #include "debug.h" -static bstring format_str(bstring s) +static void print_str(const unsigned char *s, int len) { - int pos = 0; - int len = blength(s); - bstring result = bfromcstr(""); - char c; - bformata(result, "\""); - while (pos < len) { - c = bchar(s, pos); - switch (c) { - case '\n': - bformata(result, "\\n"); - break; - case '"': - bformata(result, "\\\""); - break; - case '\\': - bformata(result, "\\\\"); - break; - default: - bformata(result, "%c", c); - } - pos++; - } - bformata(result, "\""); - return result; + int i; + + if (len < 0) + len = strlen(s); + + putchar('"'); + for (i = 0; i < len; ++i) { + unsigned char c = s[i]; + + switch (c) { + case '\n': + printf("\\n"); + break; + case '"': + printf("\\\""); + break; + case '\\': + printf("\\\\"); + break; + default: + putchar((int)c); + } + } + putchar('"'); } // Functions to pretty-print inline and block lists, for debugging. // Prettyprint an inline list, for debugging. extern void print_blocks(block* b, int indent) { - struct ListData * data; - while(b != NULL) { - // printf("%3d %3d %3d| ", b->start_line, b->start_column, b->end_line); - for (int i=0; i < indent; i++) { - putchar(' '); - } - switch(b->tag) { - case document: - printf("document\n"); - print_blocks(b->children, indent + 2); - break; - case block_quote: - printf("block_quote\n"); - print_blocks(b->children, indent + 2); - break; - case list_item: - data = &(b->attributes.list_data); - printf("list_item\n"); - print_blocks(b->children, indent + 2); - break; - case list: - data = &(b->attributes.list_data); - if (data->list_type == ordered) { - printf("list (type=ordered tight=%s start=%d delim=%s)\n", - (data->tight ? "true" : "false"), - data->start, - (data->delimiter == parens ? "parens" : "period")); - } else { - printf("list (type=bullet tight=%s bullet_char=%c)\n", - (data->tight ? "true" : "false"), - data->bullet_char); - } - print_blocks(b->children, indent + 2); - break; - case atx_header: - printf("atx_header (level=%d)\n", b->attributes.header_level); - print_inlines(b->inline_content, indent + 2); - break; - case setext_header: - printf("setext_header (level=%d)\n", b->attributes.header_level); - print_inlines(b->inline_content, indent + 2); - break; - case paragraph: - printf("paragraph\n"); - print_inlines(b->inline_content, indent + 2); - break; - case hrule: - printf("hrule\n"); - break; - case indented_code: - printf("indented_code %s\n", format_str(b->string_content)->data); - break; - case fenced_code: - printf("fenced_code length=%d info=%s %s\n", - b->attributes.fenced_code_data.fence_length, - format_str(b->attributes.fenced_code_data.info)->data, - format_str(b->string_content)->data); - break; - case html_block: - printf("html_block %s\n", format_str(b->string_content)->data); - break; - case reference_def: - printf("reference_def\n"); - break; - default: - log_warn("block type %d not implemented\n", b->tag); - break; - } - b = b->next; - } + struct ListData *data; + + while(b != NULL) { + // printf("%3d %3d %3d| ", b->start_line, b->start_column, b->end_line); + for (int i=0; i < indent; i++) { + putchar(' '); + } + + switch(b->tag) { + case document: + printf("document\n"); + print_blocks(b->children, indent + 2); + break; + case block_quote: + printf("block_quote\n"); + print_blocks(b->children, indent + 2); + break; + case list_item: + data = &(b->attributes.list_data); + printf("list_item\n"); + print_blocks(b->children, indent + 2); + break; + case list: + data = &(b->attributes.list_data); + if (data->list_type == ordered) { + printf("list (type=ordered tight=%s start=%d delim=%s)\n", + (data->tight ? "true" : "false"), + data->start, + (data->delimiter == parens ? "parens" : "period")); + } else { + printf("list (type=bullet tight=%s bullet_char=%c)\n", + (data->tight ? "true" : "false"), + data->bullet_char); + } + print_blocks(b->children, indent + 2); + break; + case atx_header: + printf("atx_header (level=%d)\n", b->attributes.header_level); + print_inlines(b->inline_content, indent + 2); + break; + case setext_header: + printf("setext_header (level=%d)\n", b->attributes.header_level); + print_inlines(b->inline_content, indent + 2); + break; + case paragraph: + printf("paragraph\n"); + print_inlines(b->inline_content, indent + 2); + break; + case hrule: + printf("hrule\n"); + break; + case indented_code: + printf("indented_code "); + print_str(b->string_content.ptr, -1); + putchar('\n'); + break; + case fenced_code: + printf("fenced_code length=%d info=", + b->attributes.fenced_code_data.fence_length); + print_str(b->attributes.fenced_code_data.info.ptr, -1); + putchar(' '); + print_str(b->string_content.ptr, -1); + putchar('\n'); + break; + case html_block: + printf("html_block "); + print_str(b->string_content.ptr, -1); + putchar('\n'); + break; + case reference_def: + printf("reference_def\n"); + break; + default: + printf("# NOT IMPLEMENTED (%d)\n", b->tag); + break; + } + b = b->next; + } } // Prettyprint an inline list, for debugging. extern void print_inlines(inl* ils, int indent) { - while(ils != NULL) { - /* - // we add 11 extra spaces for the line/column info - for (int i=0; i < 11; i++) { - putchar(' '); - } - putchar('|'); - putchar(' '); - */ - for (int i=0; i < indent; i++) { - putchar(' '); - } - switch(ils->tag) { - case str: - printf("str %s\n", format_str(ils->content.literal)->data); - break; - case linebreak: - printf("linebreak\n"); - break; - case softbreak: - printf("softbreak\n"); - break; - case code: - printf("code %s\n", format_str(ils->content.literal)->data); - break; - case raw_html: - printf("html %s\n", format_str(ils->content.literal)->data); - break; - case entity: - printf("entity %s\n", format_str(ils->content.literal)->data); - break; - case link: - printf("link url=%s title=%s\n", - format_str(ils->content.linkable.url)->data, - format_str(ils->content.linkable.title)->data); - print_inlines(ils->content.linkable.label, indent + 2); - break; - case image: - printf("image url=%s title=%s\n", - format_str(ils->content.linkable.url)->data, - format_str(ils->content.linkable.title)->data); - print_inlines(ils->content.linkable.label, indent + 2); - break; - case strong: - printf("strong\n"); - print_inlines(ils->content.linkable.label, indent + 2); - break; - case emph: - printf("emph\n"); - print_inlines(ils->content.linkable.label, indent + 2); - break; - } - ils = ils->next; - } + while(ils != NULL) { + for (int i=0; i < indent; i++) { + putchar(' '); + } + switch(ils->tag) { + case str: + printf("str "); + print_str(ils->content.literal.data, ils->content.literal.len); + putchar('\n'); + break; + case linebreak: + printf("linebreak\n"); + break; + case softbreak: + printf("softbreak\n"); + break; + case code: + printf("code "); + print_str(ils->content.literal.data, ils->content.literal.len); + putchar('\n'); + break; + case raw_html: + printf("html "); + print_str(ils->content.literal.data, ils->content.literal.len); + putchar('\n'); + break; + case entity: + printf("entity "); + print_str(ils->content.literal.data, ils->content.literal.len); + putchar('\n'); + break; + case link: + case image: + printf("%s url=", ils->tag == link ? "link" : "image"); + print_str(ils->content.linkable.url, -1); + if (ils->content.linkable.title) { + printf(" title="); + print_str(ils->content.linkable.title, -1); + } + putchar('\n'); + print_inlines(ils->content.linkable.label, indent + 2); + break; + case strong: + printf("strong\n"); + print_inlines(ils->content.linkable.label, indent + 2); + break; + case emph: + printf("emph\n"); + print_inlines(ils->content.linkable.label, indent + 2); + break; + } + ils = ils->next; + } } diff --git a/src/stmd.h b/src/stmd.h index eb1b989..dc24235 100644 --- a/src/stmd.h +++ b/src/stmd.h @@ -105,19 +105,14 @@ extern block* add_child(block* parent, int block_type, int start_line, int start_column); void free_blocks(block* e); -block *stmd_parse_document(const char *buffer, size_t len); - -// FOR NOW: -void process_inlines(block* cur, reference** refmap); -void incorporate_line(gh_buf *ln, int line_number, block** curptr); -void finalize(block* b, int line_number); +extern block *stmd_parse_document(const unsigned char *buffer, size_t len); +extern block *stmd_parse_file(FILE *f); void print_inlines(inl* ils, int indent); void print_blocks(block* blk, int indent); -/* TODO */ -// int blocks_to_html(block* b, bstring* result, bool tight); -// int inlines_to_html(inl* b, bstring* result); +void blocks_to_html(gh_buf *html, block *b, bool tight); +void inlines_to_html(gh_buf *html, inl *b); void utf8proc_case_fold(gh_buf *dest, const unsigned char *str, int len); diff --git a/src/utf8.c b/src/utf8.c index 1a5df9e..e3f8dd3 100644 --- a/src/utf8.c +++ b/src/utf8.c @@ -1,6 +1,8 @@ #include -#include "bstrlib.h" -#include "debug.h" +#include +#include + +#include "stmd.h" static const int8_t utf8proc_utf8class[256] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, diff --git a/src/utf8.h b/src/utf8.h deleted file mode 100644 index fe59a90..0000000 --- a/src/utf8.h +++ /dev/null @@ -1,6 +0,0 @@ -#include -#include "bstrlib.h" - -extern unsigned char * from_utf8(unsigned char * s, unsigned int *n); -extern int to_utf8(unsigned int c, bstring dest); -extern bstring case_fold(bstring source); -- cgit v1.2.3 From a7314deae649646f1f7ce5ede972641b5b62538c Mon Sep 17 00:00:00 2001 From: Vicent Marti Date: Wed, 3 Sep 2014 03:40:23 +0200 Subject: 338/103 --- Makefile | 4 +- src/blocks.c | 173 +++++++++++++++++----------------- src/buffer.c | 26 ++++- src/buffer.h | 2 +- src/html/houdini_href_e.c | 10 +- src/html/houdini_html_e.c | 10 +- src/html/html.c | 4 +- src/inlines.c | 235 ++++++++++++++++++---------------------------- src/print.c | 2 +- src/scanners.h | 28 +++--- src/scanners.re | 85 +++++++---------- src/stmd.h | 16 ++-- 12 files changed, 261 insertions(+), 334 deletions(-) (limited to 'Makefile') diff --git a/Makefile b/Makefile index d14a928..89ec68c 100644 --- a/Makefile +++ b/Makefile @@ -1,5 +1,5 @@ -CFLAGS=-ggdb3 -O0 -Wall -Wextra -std=c99 -Isrc $(OPTFLAGS) -LDFLAGS=-ggdb3 -O0 -Wall -Werror +CFLAGS=-ggdb3 -O0 -Wall -Wextra -Wno-unused-variable -std=c99 -Isrc $(OPTFLAGS) +LDFLAGS=-ggdb3 -O0 -Wall -Wno-unused-variable # -Werror SRCDIR=src DATADIR=data diff --git a/src/blocks.c b/src/blocks.c index 42f20db..94ff986 100644 --- a/src/blocks.c +++ b/src/blocks.c @@ -8,6 +8,8 @@ #include "scanners.h" #include "uthash.h" +#define peek_at(i, n) (i)->data[n] + static void incorporate_line(gh_buf *ln, int line_number, block** curptr); static void finalize(block* b, int line_number); @@ -27,7 +29,6 @@ static block* make_block(int tag, int start_line, int start_column) e->top = NULL; e->attributes.refmap = NULL; gh_buf_init(&e->string_content, 32); - e->string_pos = 0; e->inline_content = NULL; e->next = NULL; e->prev = NULL; @@ -80,10 +81,10 @@ static inline bool accepts_lines(int block_type) block_type == fenced_code); } -static void add_line(block* block, gh_buf *ln, int offset) +static void add_line(block* block, chunk *ch, int offset) { assert(block->open); - gh_buf_put(&block->string_content, ln->ptr + offset, ln->size - offset); + gh_buf_put(&block->string_content, ch->data + offset, ch->len - offset); } static void remove_trailing_blank_lines(gh_buf *ln) @@ -104,7 +105,7 @@ static void remove_trailing_blank_lines(gh_buf *ln) i = gh_buf_strchr(ln, '\n', i); if (i >= 0) - gh_buf_truncate(ln, i + 1); + gh_buf_truncate(ln, i); } // Check to see if a block ends with a blank line, descending @@ -162,12 +163,12 @@ static void finalize(block* b, int line_number) switch (b->tag) { case paragraph: pos = 0; - while (gh_buf_at(&b->string_content, b->string_pos) == '[' && - (pos = parse_reference(&b->string_content, b->string_pos, - b->top->attributes.refmap))) { - b->string_pos = pos; + while (gh_buf_at(&b->string_content, 0) == '[' && + (pos = parse_reference(&b->string_content, b->top->attributes.refmap))) { + + gh_buf_drop(&b->string_content, pos); } - if (is_blank(&b->string_content, b->string_pos)) { + if (is_blank(&b->string_content, 0)) { b->tag = reference_def; } break; @@ -179,14 +180,16 @@ static void finalize(block* b, int line_number) case fenced_code: // first line of contents becomes info - firstlinelen = gh_buf_strchr(&b->string_content, '\n', b->string_pos); + firstlinelen = gh_buf_strchr(&b->string_content, '\n', 0); + + gh_buf_init(&b->attributes.fenced_code_data.info, 0); gh_buf_set( &b->attributes.fenced_code_data.info, - b->string_content.ptr + b->string_pos, + b->string_content.ptr, firstlinelen ); - b->string_pos = firstlinelen + 1; + gh_buf_drop(&b->string_content, firstlinelen + 1); gh_buf_trim(&b->attributes.fenced_code_data.info); unescape_buffer(&b->attributes.fenced_code_data.info); @@ -281,7 +284,7 @@ void process_inlines(block* cur, reference** refmap) case paragraph: case atx_header: case setext_header: - cur->inline_content = parse_inlines(&cur->string_content, cur->string_pos, refmap); + cur->inline_content = parse_inlines(&cur->string_content, refmap); // MEM // gh_buf_free(&cur->string_content); break; @@ -300,19 +303,18 @@ void process_inlines(block* cur, reference** refmap) // Attempts to parse a list item marker (bullet or enumerated). // On success, returns length of the marker, and populates // data with the details. On failure, returns 0. -static int parse_list_marker(gh_buf *ln, int pos, - struct ListData ** dataptr) +static int parse_list_marker(chunk *input, int pos, struct ListData ** dataptr) { - char c; + unsigned char c; int startpos; struct ListData * data; startpos = pos; - c = gh_buf_at(ln, pos); + c = peek_at(input, pos); - if ((c == '*' || c == '-' || c == '+') && !scan_hrule(ln, pos)) { + if ((c == '*' || c == '-' || c == '+') && !scan_hrule(input, pos)) { pos++; - if (!isspace(gh_buf_at(ln, pos))) { + if (!isspace(peek_at(input, pos))) { return 0; } data = malloc(sizeof(struct ListData)); @@ -327,14 +329,14 @@ static int parse_list_marker(gh_buf *ln, int pos, int start = 0; do { - start = (10 * start) + (gh_buf_at(ln, pos) - '0'); + start = (10 * start) + (peek_at(input, pos) - '0'); pos++; - } while (isdigit(gh_buf_at(ln, pos))); + } while (isdigit(peek_at(input, pos))); - c = gh_buf_at(ln, pos); + c = peek_at(input, pos); if (c == '.' || c == ')') { pos++; - if (!isspace(gh_buf_at(ln, pos))) { + if (!isspace(peek_at(input, pos))) { return 0; } data = malloc(sizeof(struct ListData)); @@ -449,8 +451,26 @@ extern block *stmd_parse_document(const unsigned char *buffer, size_t len) return finalize_document(document, linenum); } +static void chop_trailing_hashtags(chunk *ch) +{ + int n; + + chunk_rtrim(ch); + n = ch->len - 1; + + // if string ends in #s, remove these: + while (n >= 0 && peek_at(ch, n) == '#') + n--; + + // the last # was escaped, so we include it. + if (n >= 0 && peek_at(ch, n) == '\\') + n++; + + ch->len = n + 1; +} + // Process one line at a time, modifying a block. -static void incorporate_line(gh_buf *ln, int line_number, block** curptr) +static void incorporate_line(gh_buf *line, int line_number, block** curptr) { block* last_matched_container; int offset = 0; @@ -464,6 +484,10 @@ static void incorporate_line(gh_buf *ln, int line_number, block** curptr) bool blank = false; int first_nonspace; int indent; + chunk input; + + input.data = line->ptr; + input.len = line->size; // container starts at the document root. container = cur->top; @@ -475,21 +499,19 @@ static void incorporate_line(gh_buf *ln, int line_number, block** curptr) container = container->last_child; first_nonspace = offset; - while (gh_buf_at(ln, first_nonspace) == ' ') { + while (peek_at(&input, first_nonspace) == ' ') { first_nonspace++; } indent = first_nonspace - offset; - blank = gh_buf_at(ln, first_nonspace) == '\n'; + blank = peek_at(&input, first_nonspace) == '\n'; if (container->tag == block_quote) { - - matched = indent <= 3 && gh_buf_at(ln, first_nonspace) == '>'; + matched = indent <= 3 && peek_at(&input, first_nonspace) == '>'; if (matched) { offset = first_nonspace + 1; - if (gh_buf_at(ln, offset) == ' ') { + if (peek_at(&input, offset) == ' ') offset++; - } } else { all_matched = false; } @@ -526,7 +548,7 @@ static void incorporate_line(gh_buf *ln, int line_number, block** curptr) // skip optional spaces of fence offset i = container->attributes.fenced_code_data.fence_offset; - while (i > 0 && gh_buf_at(ln, offset) == ' ') { + while (i > 0 && peek_at(&input, offset) == ' ') { offset++; i--; } @@ -564,15 +586,13 @@ static void incorporate_line(gh_buf *ln, int line_number, block** curptr) container->tag != html_block) { first_nonspace = offset; - while (gh_buf_at(ln, first_nonspace) == ' ') { + while (peek_at(&input, first_nonspace) == ' ') first_nonspace++; - } indent = first_nonspace - offset; - blank = gh_buf_at(ln, first_nonspace) == '\n'; + blank = peek_at(&input, first_nonspace) == '\n'; if (indent >= CODE_INDENT) { - if (cur->tag != paragraph && !blank) { offset += CODE_INDENT; container = add_child(container, indented_code, line_number, offset + 1); @@ -580,76 +600,70 @@ static void incorporate_line(gh_buf *ln, int line_number, block** curptr) break; } - } else if (gh_buf_at(ln, first_nonspace) == '>') { + } else if (peek_at(&input, first_nonspace) == '>') { offset = first_nonspace + 1; // optional following character - if (gh_buf_at(ln, offset) == ' ') { + if (peek_at(&input, offset) == ' ') offset++; - } container = add_child(container, block_quote, line_number, offset + 1); - } else if ((matched = scan_atx_header_start(ln, first_nonspace))) { + } else if ((matched = scan_atx_header_start(&input, first_nonspace))) { offset = first_nonspace + matched; container = add_child(container, atx_header, line_number, offset + 1); - int hashpos = gh_buf_strchr(ln, '#', first_nonspace); - assert(hashpos >= 0); - + int hashpos = chunk_strchr(&input, '#', first_nonspace); int level = 0; - while (gh_buf_at(ln, hashpos) == '#') { + + while (peek_at(&input, hashpos) == '#') { level++; hashpos++; } container->attributes.header_level = level; - } else if ((matched = scan_open_code_fence(ln, first_nonspace))) { + } else if ((matched = scan_open_code_fence(&input, first_nonspace))) { - container = add_child(container, fenced_code, line_number, - first_nonspace + 1); - container->attributes.fenced_code_data.fence_char = gh_buf_at(ln, - first_nonspace); + container = add_child(container, fenced_code, line_number, first_nonspace + 1); + container->attributes.fenced_code_data.fence_char = peek_at(&input, first_nonspace); container->attributes.fenced_code_data.fence_length = matched; - container->attributes.fenced_code_data.fence_offset = - first_nonspace - offset; + container->attributes.fenced_code_data.fence_offset = first_nonspace - offset; offset = first_nonspace + matched; - } else if ((matched = scan_html_block_tag(ln, first_nonspace))) { + } else if ((matched = scan_html_block_tag(&input, first_nonspace))) { - container = add_child(container, html_block, line_number, - first_nonspace + 1); + container = add_child(container, html_block, line_number, first_nonspace + 1); // note, we don't adjust offset because the tag is part of the text } else if (container->tag == paragraph && - (lev = scan_setext_header_line(ln, first_nonspace)) && + (lev = scan_setext_header_line(&input, first_nonspace)) && // check that there is only one line in the paragraph: gh_buf_strrchr(&container->string_content, '\n', gh_buf_len(&container->string_content) - 2) < 0) { container->tag = setext_header; container->attributes.header_level = lev; - offset = gh_buf_len(ln) - 1; + offset = input.len - 1; } else if (!(container->tag == paragraph && !all_matched) && - (matched = scan_hrule(ln, first_nonspace))) { + (matched = scan_hrule(&input, first_nonspace))) { // it's only now that we know the line is not part of a setext header: container = add_child(container, hrule, line_number, first_nonspace + 1); finalize(container, line_number); container = container->parent; - offset = gh_buf_len(ln) - 1; + offset = input.len - 1; - } else if ((matched = parse_list_marker(ln, first_nonspace, &data))) { + } else if ((matched = parse_list_marker(&input, first_nonspace, &data))) { // compute padding: offset = first_nonspace + matched; i = 0; - while (i <= 5 && gh_buf_at(ln, offset + i) == ' ') { + while (i <= 5 && peek_at(&input, offset + i) == ' ') { i++; } // i = number of spaces after marker, up to 5 - if (i >= 5 || i < 1 || gh_buf_at(ln, offset) == '\n') { + if (i >= 5 || i < 1 || peek_at(&input, offset) == '\n') { data->padding = matched + 1; if (i > 0) { offset += 1; @@ -674,6 +688,7 @@ static void incorporate_line(gh_buf *ln, int line_number, block** curptr) // add the list item container = add_child(container, list_item, line_number, first_nonspace + 1); + /* TODO: static */ container->attributes.list_data = *data; free(data); @@ -691,12 +706,11 @@ static void incorporate_line(gh_buf *ln, int line_number, block** curptr) // appropriate container. first_nonspace = offset; - while (gh_buf_at(ln, first_nonspace) == ' ') { + while (peek_at(&input, first_nonspace) == ' ') first_nonspace++; - } indent = first_nonspace - offset; - blank = gh_buf_at(ln, first_nonspace) == '\n'; + blank = peek_at(&input, first_nonspace) == '\n'; // block quote lines are never blank as they start with > // and we don't count blanks in fenced code for purposes of tight/loose @@ -721,13 +735,12 @@ static void incorporate_line(gh_buf *ln, int line_number, block** curptr) cur->tag == paragraph && gh_buf_len(&cur->string_content) > 0) { - add_line(cur, ln, offset); + add_line(cur, &input, offset); } else { // not a lazy continuation // finalize any blocks that were not matched and set cur to container: while (cur != last_matched_container) { - finalize(cur, line_number); cur = cur->parent; assert(cur != NULL); @@ -735,58 +748,46 @@ static void incorporate_line(gh_buf *ln, int line_number, block** curptr) if (container->tag == indented_code) { - add_line(container, ln, offset); + add_line(container, &input, offset); } else if (container->tag == fenced_code) { matched = (indent <= 3 - && gh_buf_at(ln, first_nonspace) == container->attributes.fenced_code_data.fence_char) - && scan_close_code_fence(ln, first_nonspace, + && peek_at(&input, first_nonspace) == container->attributes.fenced_code_data.fence_char) + && scan_close_code_fence(&input, first_nonspace, container->attributes.fenced_code_data.fence_length); if (matched) { // if closing fence, don't add line to container; instead, close it: finalize(container, line_number); container = container->parent; // back up to parent } else { - add_line(container, ln, offset); + add_line(container, &input, offset); } } else if (container->tag == html_block) { - add_line(container, ln, offset); + add_line(container, &input, offset); } else if (blank) { // ??? do nothing } else if (container->tag == atx_header) { - // chop off trailing ###s...use a scanner? - gh_buf_trim(ln); - int p = gh_buf_len(ln) - 1; - - // if string ends in #s, remove these: - while (gh_buf_at(ln, p) == '#') { - p--; - } - if (gh_buf_at(ln, p) == '\\') { - // the last # was escaped, so we include it. - p++; - } - gh_buf_truncate(ln, p + 1); - add_line(container, ln, first_nonspace); + chop_trailing_hashtags(&input); + add_line(container, &input, first_nonspace); finalize(container, line_number); container = container->parent; } else if (accepts_lines(container->tag)) { - add_line(container, ln, first_nonspace); + add_line(container, &input, first_nonspace); } else if (container->tag != hrule && container->tag != setext_header) { // create paragraph container for line container = add_child(container, paragraph, line_number, first_nonspace + 1); - add_line(container, ln, first_nonspace); + add_line(container, &input, first_nonspace); } else { assert(false); diff --git a/src/buffer.c b/src/buffer.c index cfc6a7e..dc4a405 100644 --- a/src/buffer.c +++ b/src/buffer.c @@ -95,7 +95,7 @@ void gh_buf_clear(gh_buf *buf) int gh_buf_set(gh_buf *buf, const unsigned char *data, int len) { - if (len == 0 || data == NULL) { + if (len <= 0 || data == NULL) { gh_buf_clear(buf); } else { if (data != buf->ptr) { @@ -125,6 +125,9 @@ int gh_buf_putc(gh_buf *buf, int c) int gh_buf_put(gh_buf *buf, const unsigned char *data, int len) { + if (len <= 0) + return 0; + ENSURE_SIZE(buf, buf->size + len + 1); memmove(buf->ptr + buf->size, data, len); buf->size += len; @@ -272,15 +275,28 @@ void gh_buf_truncate(gh_buf *buf, int len) } } +void gh_buf_drop(gh_buf *buf, int n) +{ + if (n > 0) { + buf->size = buf->size - n; + if (buf->size) + memmove(buf->ptr, buf->ptr + n, buf->size); + + buf->ptr[buf->size] = '\0'; + } +} + void gh_buf_trim(gh_buf *buf) { - /* TODO: leading whitespace? */ - /* + int i = 0; + + if (!buf->size) + return; + while (i < buf->size && isspace(buf->ptr[i])) i++; - gh_buf_truncate(buf, i); - */ + gh_buf_drop(buf, i); /* rtrim */ while (buf->size > 0) { diff --git a/src/buffer.h b/src/buffer.h index 422ef02..0d5143e 100644 --- a/src/buffer.h +++ b/src/buffer.h @@ -105,8 +105,8 @@ extern void gh_buf_clear(gh_buf *buf); int gh_buf_strchr(const gh_buf *buf, int c, int pos); int gh_buf_strrchr(const gh_buf *buf, int c, int pos); +void gh_buf_drop(gh_buf *buf, int n); void gh_buf_truncate(gh_buf *buf, int len); -void gh_buf_ltruncate(gh_buf *buf, int len); void gh_buf_trim(gh_buf *buf); #endif diff --git a/src/html/houdini_href_e.c b/src/html/houdini_href_e.c index 59fe850..b2a7d79 100644 --- a/src/html/houdini_href_e.c +++ b/src/html/houdini_href_e.c @@ -62,16 +62,8 @@ houdini_escape_href(gh_buf *ob, const uint8_t *src, size_t size) while (i < size && HREF_SAFE[src[i]] != 0) i++; - if (likely(i > org)) { - if (unlikely(org == 0)) { - if (i >= size) - return 0; - - gh_buf_grow(ob, HOUDINI_ESCAPED_SIZE(size)); - } - + if (likely(i > org)) gh_buf_put(ob, src + org, i - org); - } /* escaping */ if (i >= size) diff --git a/src/html/houdini_html_e.c b/src/html/houdini_html_e.c index 316c5ce..5cdd3dd 100644 --- a/src/html/houdini_html_e.c +++ b/src/html/houdini_html_e.c @@ -54,16 +54,8 @@ houdini_escape_html0(gh_buf *ob, const uint8_t *src, size_t size, int secure) while (i < size && (esc = HTML_ESCAPE_TABLE[src[i]]) == 0) i++; - if (i > org) { - if (unlikely(org == 0)) { - if (i >= size) - return 0; - - gh_buf_grow(ob, HOUDINI_ESCAPED_SIZE(size)); - } - + if (i > org) gh_buf_put(ob, src + org, i - org); - } /* escaping */ if (unlikely(i >= size)) diff --git a/src/html/html.c b/src/html/html.c index 2f160ca..27ffe58 100644 --- a/src/html/html.c +++ b/src/html/html.c @@ -68,7 +68,7 @@ void blocks_to_html(gh_buf *html, block *b, bool tight) cr(html); gh_buf_puts(html, "
  • "); blocks_to_html(html, b->children, tight); - gh_buf_trim(html); + gh_buf_trim(html); /* TODO: rtrim */ gh_buf_puts(html, "
    • "); cr(html); break; @@ -106,7 +106,7 @@ void blocks_to_html(gh_buf *html, block *b, bool tight) cr(html); gh_buf_puts(html, "
    ");
 				escape_html(html, b->string_content.ptr, b->string_content.size);
-				gh_buf_puts(html, "
    "); + gh_buf_puts(html, ""); cr(html); break; diff --git a/src/inlines.c b/src/inlines.c index 7b48ad9..ef27a24 100644 --- a/src/inlines.c +++ b/src/inlines.c @@ -9,10 +9,10 @@ #include "scanners.h" typedef struct Subject { - const gh_buf *buffer; - int pos; - reference** reference_map; - int label_nestlevel; + chunk input; + int pos; + int label_nestlevel; + reference** reference_map; } subject; reference* lookup_reference(reference** refmap, chunk *label); @@ -27,12 +27,16 @@ inline static void chunk_trim(chunk *c); inline static chunk chunk_literal(const char *data); inline static chunk chunk_buf_detach(gh_buf *buf); -inline static chunk chunk_buf(const gh_buf *buf, int pos, int len); +inline static chunk chunk_dup(const chunk *ch, int pos, int len); static inl *parse_chunk_inlines(chunk *chunk, reference** refmap); static inl *parse_inlines_while(subject* subj, int (*f)(subject*)); static int parse_inline(subject* subj, inl ** last); +static void subject_from_chunk(subject *e, chunk *chunk, reference** refmap); +static void subject_from_buf(subject *e, gh_buf *buffer, reference** refmap); +static int subject_find_special_char(subject *subj); + extern void free_reference(reference *ref) { free(ref->label); free(ref->url); @@ -101,10 +105,12 @@ extern reference* make_reference(chunk *label, chunk *url, chunk *title) extern void add_reference(reference** refmap, reference* ref) { reference * t = NULL; - HASH_FIND(hh, *refmap, (char*)ref->label, (unsigned)strlen(ref->label), t); + const char *label = (const char *)ref->label; + + HASH_FIND(hh, *refmap, label, strlen(label), t); if (t == NULL) { - HASH_ADD_KEYPTR(hh, *refmap, (char*)ref->label, (unsigned)strlen(ref->label), ref); + HASH_ADD_KEYPTR(hh, *refmap, label, strlen(label), ref); } else { free_reference(ref); // we free this now since it won't be in the refmap } @@ -210,87 +216,49 @@ inline static inl* append_inlines(inl* a, inl* b) return a; } -// Make a 'subject' from an input string. -static void init_subject(subject *e, gh_buf *buffer, int input_pos, reference** refmap) +static void subject_from_buf(subject *e, gh_buf *buffer, reference** refmap) { - e->buffer = buffer; - e->pos = input_pos; + e->input.data = buffer->ptr; + e->input.len = buffer->size; + e->input.alloc = 0; + e->pos = 0; e->label_nestlevel = 0; e->reference_map = refmap; -} - -inline static int isbacktick(int c) -{ - return (c == '`'); -} - -inline static void chunk_free(chunk *c) -{ - if (c->alloc) - free((char *)c->data); - - c->data = NULL; - c->alloc = 0; - c->len = 0; -} - -inline static void chunk_trim(chunk *c) -{ - while (c->len && isspace(c->data[0])) { - c->data++; - c->len--; - } - - while (c->len > 0) { - if (!isspace(c->data[c->len - 1])) - break; - c->len--; - } + chunk_rtrim(&e->input); } -inline static unsigned char *chunk_to_cstr(chunk *c) +static void subject_from_chunk(subject *e, chunk *chunk, reference** refmap) { - unsigned char *str; - - str = malloc(c->len + 1); - memcpy(str, c->data, c->len); - str[c->len] = 0; + e->input.data = chunk->data; + e->input.len = chunk->len; + e->input.alloc = 0; + e->pos = 0; + e->label_nestlevel = 0; + e->reference_map = refmap; - return str; + chunk_rtrim(&e->input); } -inline static chunk chunk_literal(const char *data) +inline static int isbacktick(int c) { - chunk c = {data, data ? strlen(data) : 0, 0}; - return c; + return (c == '`'); } -inline static chunk chunk_buf(const gh_buf *buf, int pos, int len) +static inline unsigned char peek_char(subject *subj) { - chunk c = {buf->ptr + pos, len, 0}; - return c; + return (subj->pos < subj->input.len) ? subj->input.data[subj->pos] : 0; } -inline static chunk chunk_buf_detach(gh_buf *buf) +static inline unsigned char peek_at(subject *subj, int pos) { - chunk c; - - c.len = buf->size; - c.data = gh_buf_detach(buf); - c.alloc = 1; - - return c; + return subj->input.data[pos]; } -// Return the next character in the subject, without advancing. -// Return 0 if at the end of the subject. -#define peek_char(subj) gh_buf_at((subj)->buffer, (subj)->pos) - // Return true if there are more characters in the subject. inline static int is_eof(subject* subj) { - return (subj->pos >= gh_buf_len(subj->buffer)); + return (subj->pos >= subj->input.len); } // Advance the subject. Doesn't check for eof. @@ -308,7 +276,7 @@ inline static chunk take_while(subject* subj, int (*f)(int)) len++; } - return chunk_buf(subj->buffer, startpos, len); + return chunk_dup(&subj->input, startpos, len); } // Try to process a backtick code span that began with a @@ -388,7 +356,7 @@ static inl* handle_backticks(subject *subj) } else { gh_buf buf = GH_BUF_INIT; - gh_buf_set(&buf, subj->buffer->ptr + startpos, endpos - startpos - openticks.len); + gh_buf_set(&buf, subj->input.data + startpos, endpos - startpos - openticks.len); gh_buf_trim(&buf); normalize_whitespace(&buf); @@ -404,7 +372,7 @@ static int scan_delims(subject* subj, char c, bool * can_open, bool * can_close) char char_before, char_after; int startpos = subj->pos; - char_before = subj->pos == 0 ? '\n' : gh_buf_at(subj->buffer, subj->pos - 1); + char_before = subj->pos == 0 ? '\n' : peek_at(subj, subj->pos - 1); while (peek_char(subj) == c) { numdelims++; advance(subj); @@ -439,7 +407,7 @@ static inl* handle_strong_emph(subject* subj, char c) numdelims = scan_delims(subj, c, &can_open, &can_close); subj->pos += numdelims; - new = make_str(chunk_buf(subj->buffer, subj->pos - numdelims, numdelims)); + new = make_str(chunk_dup(&subj->input, subj->pos - numdelims, numdelims)); *last = new; first_head = new; result = new; @@ -488,7 +456,7 @@ static inl* handle_strong_emph(subject* subj, char c) numdelims = scan_delims(subj, c, &can_open, &can_close); if (can_close && numdelims >= 1 && numdelims <= 3 && numdelims != first_close_delims) { - new = make_str(chunk_buf(subj->buffer, subj->pos, numdelims)); + new = make_str(chunk_dup(&subj->input, subj->pos, numdelims)); append_inlines(*last, new); *last = new; if (first_close_delims == 1 && numdelims > 2) { @@ -554,7 +522,7 @@ static inl* handle_backslash(subject *subj) unsigned char nextchar = peek_char(subj); if (ispunct(nextchar)) { // only ascii symbols and newline can be escaped advance(subj); - return make_str(chunk_buf(subj->buffer, subj->pos - 1, 1)); + return make_str(chunk_dup(&subj->input, subj->pos - 1, 1)); } else if (nextchar == '\n') { advance(subj); return make_linebreak(); @@ -569,9 +537,9 @@ static inl* handle_entity(subject* subj) { int match; inl *result; - match = scan_entity(subj->buffer, subj->pos); + match = scan_entity(&subj->input, subj->pos); if (match) { - result = make_entity(chunk_buf(subj->buffer, subj->pos, match)); + result = make_entity(chunk_dup(&subj->input, subj->pos, match)); subj->pos += match; } else { advance(subj); @@ -584,15 +552,13 @@ static inl* handle_entity(subject* subj) // Returns an inline sequence consisting of str and entity elements. static inl *make_str_with_entities(chunk *content) { - inl * result = NULL; - inl * new; + inl *result = NULL; + inl *new; int searchpos; char c; subject subj; - gh_buf content_buf = GH_BUF_INIT; - gh_buf_set(&content_buf, content->data, content->len); - init_subject(&subj, &content_buf, 0, NULL); + subject_from_chunk(&subj, content, NULL); while ((c = peek_char(&subj))) { switch (c) { @@ -600,18 +566,13 @@ static inl *make_str_with_entities(chunk *content) new = handle_entity(&subj); break; default: - searchpos = gh_buf_strchr(subj.buffer, '&', subj.pos); - if (searchpos < 0) { - searchpos = gh_buf_len(subj.buffer); - } - - new = make_str(chunk_buf(subj.buffer, subj.pos, searchpos - subj.pos)); + searchpos = chunk_strchr(&subj.input, '&', subj.pos); + new = make_str(chunk_dup(&subj.input, subj.pos, searchpos - subj.pos)); subj.pos = searchpos; } result = append_inlines(result, new); } - gh_buf_free(&content_buf); return result; } @@ -678,9 +639,9 @@ static inl* handle_pointy_brace(subject* subj) advance(subj); // advance past first < // first try to match a URL autolink - matchlen = scan_autolink_uri(subj->buffer, subj->pos); + matchlen = scan_autolink_uri(&subj->input, subj->pos); if (matchlen > 0) { - contents = chunk_buf(subj->buffer, subj->pos, matchlen - 1); + contents = chunk_dup(&subj->input, subj->pos, matchlen - 1); subj->pos += matchlen; return make_link( @@ -691,11 +652,11 @@ static inl* handle_pointy_brace(subject* subj) } // next try to match an email autolink - matchlen = scan_autolink_email(subj->buffer, subj->pos); + matchlen = scan_autolink_email(&subj->input, subj->pos); if (matchlen > 0) { gh_buf mail_url = GH_BUF_INIT; - contents = chunk_buf(subj->buffer, subj->pos, matchlen - 1); + contents = chunk_dup(&subj->input, subj->pos, matchlen - 1); subj->pos += matchlen; gh_buf_puts(&mail_url, "mailto:"); @@ -709,9 +670,9 @@ static inl* handle_pointy_brace(subject* subj) } // finally, try to match an html tag - matchlen = scan_html_tag(subj->buffer, subj->pos); + matchlen = scan_html_tag(&subj->input, subj->pos); if (matchlen > 0) { - contents = chunk_buf(subj->buffer, subj->pos - 1, matchlen + 1); + contents = chunk_dup(&subj->input, subj->pos - 1, matchlen + 1); subj->pos += matchlen; return make_raw_html(contents); } @@ -776,12 +737,7 @@ static int link_label(subject* subj, chunk *raw_label) } } if (c == ']') { - *raw_label = chunk_buf( - subj->buffer, - startpos + 1, - subj->pos - (startpos + 1) - ); - + *raw_label = chunk_dup(&subj->input, startpos + 1, subj->pos - (startpos + 1)); subj->label_nestlevel = 0; advance(subj); // advance past ] return 1; @@ -813,25 +769,25 @@ static inl* handle_left_bracket(subject* subj) if (found_label) { if (peek_char(subj) == '(' && - ((sps = scan_spacechars(subj->buffer, subj->pos + 1)) > -1) && - ((n = scan_link_url(subj->buffer, subj->pos + 1 + sps)) > -1)) { + ((sps = scan_spacechars(&subj->input, subj->pos + 1)) > -1) && + ((n = scan_link_url(&subj->input, subj->pos + 1 + sps)) > -1)) { // try to parse an explicit link: starturl = subj->pos + 1 + sps; // after ( endurl = starturl + n; - starttitle = endurl + scan_spacechars(subj->buffer, endurl); + starttitle = endurl + scan_spacechars(&subj->input, endurl); // ensure there are spaces btw url and title endtitle = (starttitle == endurl) ? starttitle : - starttitle + scan_link_title(subj->buffer, starttitle); + starttitle + scan_link_title(&subj->input, starttitle); - endall = endtitle + scan_spacechars(subj->buffer, endtitle); + endall = endtitle + scan_spacechars(&subj->input, endtitle); - if (gh_buf_at(subj->buffer, endall) == ')') { + if (peek_at(subj, endall) == ')') { subj->pos = endall + 1; - url = chunk_buf(subj->buffer, starturl, endurl - starturl); - title = chunk_buf(subj->buffer, starttitle, endtitle - starttitle); + url = chunk_dup(&subj->input, starturl, endurl - starturl); + title = chunk_dup(&subj->input, starttitle, endtitle - starttitle); lab = parse_chunk_inlines(&rawlabel, NULL); return make_link(lab, url, title); @@ -850,7 +806,7 @@ static inl* handle_left_bracket(subject* subj) // Check for reference link. // First, see if there's another label: - subj->pos = subj->pos + scan_spacechars(subj->buffer, endlabel); + subj->pos = subj->pos + scan_spacechars(&subj->input, endlabel); reflabel = rawlabel; // if followed by a nonempty link label, we change reflabel to it: @@ -892,8 +848,8 @@ static inl* handle_newline(subject *subj) advance(subj); } if (nlpos > 1 && - gh_buf_at(subj->buffer, nlpos - 1) == ' ' && - gh_buf_at(subj->buffer, nlpos - 2) == ' ') { + peek_at(subj, nlpos - 1) == ' ' && + peek_at(subj, nlpos - 2) == ' ') { return make_linebreak(); } else { return make_softbreak(); @@ -917,30 +873,22 @@ extern inl* parse_inlines_while(subject* subj, int (*f)(subject*)) inl *parse_chunk_inlines(chunk *chunk, reference** refmap) { - inl *result; subject subj; - gh_buf full_chunk = GH_BUF_INIT; - - gh_buf_set(&full_chunk, chunk->data, chunk->len); - init_subject(&subj, &full_chunk, 0, refmap); - result = parse_inlines_while(&subj, not_eof); - - gh_buf_free(&full_chunk); - return result; + subject_from_chunk(&subj, chunk, refmap); + return parse_inlines_while(&subj, not_eof); } -static int find_special_char(subject *subj) +static int subject_find_special_char(subject *subj) { int n = subj->pos + 1; - int size = (int)gh_buf_len(subj->buffer); - while (n < size) { - if (strchr("\n\\`&_*[]buffer, n))) + while (n < subj->input.len) { + if (strchr("\n\\`&_*[]input.data[n])) return n; n++; } - return -1; + return subj->input.len; } // Parse an inline, advancing subject, and add it to last element. @@ -973,11 +921,13 @@ static int parse_inline(subject* subj, inl ** last) new = handle_pointy_brace(subj); break; case '_': - if (subj->pos > 0 && (isalnum(gh_buf_at(subj->buffer, subj->pos - 1)) || - gh_buf_at(subj->buffer, subj->pos - 1) == '_')) { - new = make_str(chunk_literal("_")); - advance(subj); - break; + if (subj->pos > 0) { + unsigned char prev = peek_at(subj, subj->pos - 1); + if (isalnum(prev) || prev == '_') { + new = make_str(chunk_literal("_")); + advance(subj); + break; + } } new = handle_strong_emph(subj, '_'); @@ -1002,18 +952,13 @@ static int parse_inline(subject* subj, inl ** last) } break; default: - text_literal: - endpos = find_special_char(subj); - if (endpos < 0) { - endpos = gh_buf_len(subj->buffer); - } - - contents = chunk_buf(subj->buffer, subj->pos, endpos - subj->pos); + endpos = subject_find_special_char(subj); + contents = chunk_dup(&subj->input, subj->pos, endpos - subj->pos); subj->pos = endpos; // if we're at a newline, strip trailing spaces. if (peek_char(subj) == '\n') { - chunk_trim(&contents); + chunk_rtrim(&contents); } new = make_str(contents); @@ -1026,10 +971,10 @@ static int parse_inline(subject* subj, inl ** last) return 1; } -extern inl* parse_inlines(gh_buf *input, int input_pos, reference** refmap) +extern inl* parse_inlines(gh_buf *input, reference** refmap) { subject subj; - init_subject(&subj, input, input_pos, refmap); + subject_from_buf(&subj, input, refmap); return parse_inlines_while(&subj, not_eof); } @@ -1048,7 +993,7 @@ void spnl(subject* subj) // Modify refmap if a reference is encountered. // Return 0 if no reference found, otherwise position of subject // after reference is parsed. -extern int parse_reference(gh_buf *input, int input_pos, reference** refmap) +extern int parse_reference(gh_buf *input, reference** refmap) { subject subj; @@ -1058,9 +1003,9 @@ extern int parse_reference(gh_buf *input, int input_pos, reference** refmap) int matchlen = 0; int beforetitle; - reference * new = NULL; + reference *new = NULL; - init_subject(&subj, input, input_pos, NULL); + subject_from_buf(&subj, input, NULL); // parse label: if (!link_label(&subj, &lab)) @@ -1075,9 +1020,9 @@ extern int parse_reference(gh_buf *input, int input_pos, reference** refmap) // parse link url: spnl(&subj); - matchlen = scan_link_url(subj.buffer, subj.pos); + matchlen = scan_link_url(&subj.input, subj.pos); if (matchlen) { - url = chunk_buf(subj.buffer, subj.pos, matchlen); + url = chunk_dup(&subj.input, subj.pos, matchlen); subj.pos += matchlen; } else { return 0; @@ -1086,9 +1031,9 @@ extern int parse_reference(gh_buf *input, int input_pos, reference** refmap) // parse optional link_title beforetitle = subj.pos; spnl(&subj); - matchlen = scan_link_title(subj.buffer, subj.pos); + matchlen = scan_link_title(&subj.input, subj.pos); if (matchlen) { - title = chunk_buf(subj.buffer, subj.pos, matchlen); + title = chunk_dup(&subj.input, subj.pos, matchlen); subj.pos += matchlen; } else { subj.pos = beforetitle; diff --git a/src/print.c b/src/print.c index 0a87925..c262995 100644 --- a/src/print.c +++ b/src/print.c @@ -9,7 +9,7 @@ static void print_str(const unsigned char *s, int len) int i; if (len < 0) - len = strlen(s); + len = strlen((char *)s); putchar('"'); for (i = 0; i < len; ++i) { diff --git a/src/scanners.h b/src/scanners.h index b6e586b..f96c42d 100644 --- a/src/scanners.h +++ b/src/scanners.h @@ -1,15 +1,15 @@ -#include "buffer.h" +#include "stmd.h" -int scan_autolink_uri(const gh_buf *s, int pos); -int scan_autolink_email(const gh_buf *s, int pos); -int scan_html_tag(const gh_buf *s, int pos); -int scan_html_block_tag(const gh_buf *s, int pos); -int scan_link_url(const gh_buf *s, int pos); -int scan_link_title(const gh_buf *s, int pos); -int scan_spacechars(const gh_buf *s, int pos); -int scan_atx_header_start(const gh_buf *s, int pos); -int scan_setext_header_line(const gh_buf *s, int pos); -int scan_hrule(const gh_buf *s, int pos); -int scan_open_code_fence(const gh_buf *s, int pos); -int scan_close_code_fence(const gh_buf *s, int pos, int len); -int scan_entity(const gh_buf *s, int pos); +int scan_autolink_uri(chunk *c, int offset); +int scan_autolink_email(chunk *c, int offset); +int scan_html_tag(chunk *c, int offset); +int scan_html_block_tag(chunk *c, int offset); +int scan_link_url(chunk *c, int offset); +int scan_link_title(chunk *c, int offset); +int scan_spacechars(chunk *c, int offset); +int scan_atx_header_start(chunk *c, int offset); +int scan_setext_header_line(chunk *c, int offset); +int scan_hrule(chunk *c, int offset); +int scan_open_code_fence(chunk *c, int offset); +int scan_close_code_fence(chunk *c, int offset, int len); +int scan_entity(chunk *c, int offset); diff --git a/src/scanners.re b/src/scanners.re index 7323ef9..5ac7c15 100644 --- a/src/scanners.re +++ b/src/scanners.re @@ -1,8 +1,15 @@ -#include "buffer.h" +#include "scanners.h" + +#define SCAN_DATA \ + const unsigned char *marker = NULL; \ + const unsigned char *p = c->data + offset; \ + const unsigned char *start = p; \ + const unsigned char *end = c->data + c->len /*!re2c re2c:define:YYCTYPE = "unsigned char"; re2c:define:YYCURSOR = p; + re2c:define:YYLIMIT = end; re2c:define:YYMARKER = marker; re2c:define:YYCTXMARKER = marker; re2c:yyfill:enable = 0; @@ -55,11 +62,9 @@ */ // Try to match URI autolink after first <, returning number of chars matched. -extern int scan_autolink_uri(const gh_buf *s, int pos) +extern int scan_autolink_uri(chunk *c, int offset) { - unsigned char * marker = NULL; - unsigned char * p = &(s->ptr[pos]); - unsigned char * start = p; + SCAN_DATA; /*!re2c scheme [:]([^\x00-\x20<>\\]|escaped_char)*[>] { return (p - start); } .? { return 0; } @@ -67,11 +72,9 @@ extern int scan_autolink_uri(const gh_buf *s, int pos) } // Try to match email autolink after first <, returning num of chars matched. -extern int scan_autolink_email(const gh_buf *s, int pos) +extern int scan_autolink_email(chunk *c, int offset) { - unsigned char * marker = NULL; - unsigned char * p = &(s->ptr[pos]); - unsigned char * start = p; + SCAN_DATA; /*!re2c [a-zA-Z0-9.!#$%&'*+/=?^_`{|}~-]+ [@] @@ -83,11 +86,9 @@ extern int scan_autolink_email(const gh_buf *s, int pos) } // Try to match an HTML tag after first <, returning num of chars matched. -extern int scan_html_tag(const gh_buf *s, int pos) +extern int scan_html_tag(chunk *c, int offset) { - unsigned char * marker = NULL; - unsigned char * p = &(s->ptr[pos]); - unsigned char * start = p; + SCAN_DATA; /*!re2c htmltag { return (p - start); } .? { return 0; } @@ -96,11 +97,9 @@ extern int scan_html_tag(const gh_buf *s, int pos) // Try to match an HTML block tag including first <, // returning num of chars matched. -extern int scan_html_block_tag(const gh_buf *s, int pos) +extern int scan_html_block_tag(chunk *c, int offset) { - unsigned char * marker = NULL; - unsigned char * p = &(s->ptr[pos]); - unsigned char * start = p; + SCAN_DATA; /*!re2c [<] [/] blocktagname (spacechar | [>]) { return (p - start); } [<] blocktagname (spacechar | [/>]) { return (p - start); } @@ -113,11 +112,9 @@ extern int scan_html_block_tag(const gh_buf *s, int pos) // This may optionally be contained in <..>; otherwise // whitespace and unbalanced right parentheses aren't allowed. // Newlines aren't ever allowed. -extern int scan_link_url(const gh_buf *s, int pos) +extern int scan_link_url(chunk *c, int offset) { - unsigned char * marker = NULL; - unsigned char * p = &(s->ptr[pos]); - unsigned char * start = p; + SCAN_DATA; /*!re2c [ \n]* [<] ([^<>\n\\\x00] | escaped_char | [\\])* [>] { return (p - start); } [ \n]* (reg_char+ | escaped_char | in_parens_nosp)* { return (p - start); } @@ -128,11 +125,9 @@ extern int scan_link_url(const gh_buf *s, int pos) // Try to match a link title (in single quotes, in double quotes, or // in parentheses), returning number of chars matched. Allow one // level of internal nesting (quotes within quotes). -extern int scan_link_title(const gh_buf *s, int pos) +extern int scan_link_title(chunk *c, int offset) { - unsigned char * marker = NULL; - unsigned char * p = &(s->ptr[pos]); - unsigned char * start = p; + SCAN_DATA; /*!re2c ["] (escaped_char|[^"\x00])* ["] { return (p - start); } ['] (escaped_char|[^'\x00])* ['] { return (p - start); } @@ -142,10 +137,9 @@ extern int scan_link_title(const gh_buf *s, int pos) } // Match space characters, including newlines. -extern int scan_spacechars(const gh_buf *s, int pos) +extern int scan_spacechars(chunk *c, int offset) { - unsigned char * p = &(s->ptr[pos]); - unsigned char * start = p; + SCAN_DATA; /*!re2c [ \t\n]* { return (p - start); } . { return 0; } @@ -153,11 +147,9 @@ extern int scan_spacechars(const gh_buf *s, int pos) } // Match ATX header start. -extern int scan_atx_header_start(const gh_buf *s, int pos) +extern int scan_atx_header_start(chunk *c, int offset) { - unsigned char * marker = NULL; - unsigned char * p = &(s->ptr[pos]); - unsigned char * start = p; + SCAN_DATA; /*!re2c [#]{1,6} ([ ]+|[\n]) { return (p - start); } .? { return 0; } @@ -166,10 +158,9 @@ extern int scan_atx_header_start(const gh_buf *s, int pos) // Match sexext header line. Return 1 for level-1 header, // 2 for level-2, 0 for no match. -extern int scan_setext_header_line(const gh_buf *s, int pos) +extern int scan_setext_header_line(chunk *c, int offset) { - unsigned char * marker = NULL; - unsigned char * p = &(s->ptr[pos]); + SCAN_DATA; /*!re2c [=]+ [ ]* [\n] { return 1; } [-]+ [ ]* [\n] { return 2; } @@ -180,11 +171,9 @@ extern int scan_setext_header_line(const gh_buf *s, int pos) // Scan a horizontal rule line: "...three or more hyphens, asterisks, // or underscores on a line by themselves. If you wish, you may use // spaces between the hyphens or asterisks." -extern int scan_hrule(const gh_buf *s, int pos) +extern int scan_hrule(chunk *c, int offset) { - unsigned char * marker = NULL; - unsigned char * p = &(s->ptr[pos]); - unsigned char * start = p; + SCAN_DATA; /*!re2c ([*][ ]*){3,} [ \t]* [\n] { return (p - start); } ([_][ ]*){3,} [ \t]* [\n] { return (p - start); } @@ -194,11 +183,9 @@ extern int scan_hrule(const gh_buf *s, int pos) } // Scan an opening code fence. -extern int scan_open_code_fence(const gh_buf *s, int pos) +extern int scan_open_code_fence(chunk *c, int offset) { - unsigned char * marker = NULL; - unsigned char * p = &(s->ptr[pos]); - unsigned char * start = p; + SCAN_DATA; /*!re2c [`]{3,} / [^`\n\x00]*[\n] { return (p - start); } [~]{3,} / [^~\n\x00]*[\n] { return (p - start); } @@ -207,11 +194,9 @@ extern int scan_open_code_fence(const gh_buf *s, int pos) } // Scan a closing code fence with length at least len. -extern int scan_close_code_fence(const gh_buf *s, int pos, int len) +extern int scan_close_code_fence(chunk *c, int offset, int len) { - unsigned char * marker = NULL; - unsigned char * p = &(s->ptr[pos]); - unsigned char * start = p; + SCAN_DATA; /*!re2c ([`]{3,} | [~]{3,}) / spacechar* [\n] { if (p - start > len) { @@ -225,11 +210,9 @@ extern int scan_close_code_fence(const gh_buf *s, int pos, int len) // Scans an entity. // Returns number of chars matched. -extern int scan_entity(const gh_buf *s, int pos) +extern int scan_entity(chunk *c, int offset) { - unsigned char * marker = NULL; - unsigned char * p = &(s->ptr[pos]); - unsigned char * start = p; + SCAN_DATA; /*!re2c [&] ([#] ([Xx][A-Fa-f0-9]{1,8}|[0-9]{1,8}) |[A-Za-z][A-Za-z0-9]{1,31} ) [;] { return (p - start); } diff --git a/src/stmd.h b/src/stmd.h index 3e284bd..4a3c399 100644 --- a/src/stmd.h +++ b/src/stmd.h @@ -1,17 +1,15 @@ +#ifndef _STDMD_H_ +#define _STDMD_H_ + #include #include #include "buffer.h" +#include "chunk.h" #include "uthash.h" #define VERSION "0.1" #define CODE_INDENT 4 -typedef struct { - const unsigned char *data; - int len; - int alloc; -} chunk; - typedef struct Inline { enum { INL_STRING, INL_SOFTBREAK, INL_LINEBREAK, INL_CODE, INL_RAW_HTML, INL_ENTITY, INL_EMPH, INL_STRONG, INL_LINK, INL_IMAGE } tag; @@ -79,7 +77,6 @@ typedef struct Block { struct Block* parent; struct Block* top; gh_buf string_content; - int string_pos; inl* inline_content; union { struct ListData list_data; @@ -91,10 +88,10 @@ typedef struct Block { struct Block * prev; } block; -inl* parse_inlines(gh_buf *input, int input_pos, reference** refmap); +inl* parse_inlines(gh_buf *input, reference** refmap); void free_inlines(inl* e); -int parse_reference(gh_buf *input, int input_pos, reference** refmap); +int parse_reference(gh_buf *input, reference** refmap); void free_reference(reference *ref); void free_reference_map(reference **refmap); @@ -117,3 +114,4 @@ void inlines_to_html(gh_buf *html, inl *b); void utf8proc_case_fold(gh_buf *dest, const unsigned char *str, int len); +#endif -- cgit v1.2.3 From 3ec98f55bd78572195f355a2ccb891df1c91b798 Mon Sep 17 00:00:00 2001 From: Vicent Marti Date: Thu, 4 Sep 2014 18:11:40 +0200 Subject: Default Makefile settings --- Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'Makefile') diff --git a/Makefile b/Makefile index 89ec68c..ed4ddd5 100644 --- a/Makefile +++ b/Makefile @@ -1,5 +1,5 @@ -CFLAGS=-ggdb3 -O0 -Wall -Wextra -Wno-unused-variable -std=c99 -Isrc $(OPTFLAGS) -LDFLAGS=-ggdb3 -O0 -Wall -Wno-unused-variable # -Werror +CFLAGS=-g -O3 -Wall -Wextra -Wno-unused-variable -std=c99 -Isrc $(OPTFLAGS) +LDFLAGS=-g -O3 -Wall -Wno-unused-variable # -Werror SRCDIR=src DATADIR=data -- cgit v1.2.3 From add5dd1b9a9ba8c58cdc6ca0bb62d287acb56278 Mon Sep 17 00:00:00 2001 From: Vicent Marti Date: Thu, 4 Sep 2014 19:40:27 +0200 Subject: Remove warnings --- Makefile | 4 ++-- src/inlines.c | 17 +++++++++++++++-- src/scanners.re | 41 ++++++++++++++++++++++++----------------- 3 files changed, 41 insertions(+), 21 deletions(-) (limited to 'Makefile') diff --git a/Makefile b/Makefile index ed4ddd5..0d2eb8b 100644 --- a/Makefile +++ b/Makefile @@ -1,5 +1,5 @@ -CFLAGS=-g -O3 -Wall -Wextra -Wno-unused-variable -std=c99 -Isrc $(OPTFLAGS) -LDFLAGS=-g -O3 -Wall -Wno-unused-variable # -Werror +CFLAGS=-g -O3 -Wall -Wextra -std=c99 -Isrc $(OPTFLAGS) +LDFLAGS=-g -O3 -Wall -Werror SRCDIR=src DATADIR=data diff --git a/src/inlines.c b/src/inlines.c index 6bb89da..5e0f3e5 100644 --- a/src/inlines.c +++ b/src/inlines.c @@ -108,13 +108,26 @@ extern void add_reference(reference** refmap, reference* ref) } } +static unsigned char *bufdup(const unsigned char *buf) +{ + unsigned char *new = NULL; + + if (!buf) { + int len = strlen((char *)buf); + new = malloc(len + 1); + memcpy(new, buf, len + 1); + } + + return new; +} + inline static node_inl* make_link_from_reference(node_inl* label, reference *ref) { node_inl* e = (node_inl*) malloc(sizeof(node_inl)); e->tag = INL_LINK; e->content.linkable.label = label; - e->content.linkable.url = strdup(ref->url); - e->content.linkable.title = ref->title ? strdup(ref->title) : NULL; + e->content.linkable.url = bufdup(ref->url); + e->content.linkable.title = bufdup(ref->title); e->next = NULL; return e; } diff --git a/src/scanners.re b/src/scanners.re index 71103f6..28aba9d 100644 --- a/src/scanners.re +++ b/src/scanners.re @@ -1,9 +1,5 @@ #include -#define SCAN_DATA \ - const unsigned char *marker = NULL; \ - const unsigned char *start = p; \ - /*!re2c re2c:define:YYCTYPE = "unsigned char"; re2c:define:YYCURSOR = p; @@ -61,7 +57,8 @@ // Try to match URI autolink after first <, returning number of chars matched. extern int _scan_autolink_uri(const unsigned char *p) { - SCAN_DATA; + const unsigned char *marker = NULL; + const unsigned char *start = p; /*!re2c scheme [:]([^\x00-\x20<>\\]|escaped_char)*[>] { return (p - start); } .? { return 0; } @@ -71,7 +68,8 @@ extern int _scan_autolink_uri(const unsigned char *p) // Try to match email autolink after first <, returning num of chars matched. extern int _scan_autolink_email(const unsigned char *p) { - SCAN_DATA; + const unsigned char *marker = NULL; + const unsigned char *start = p; /*!re2c [a-zA-Z0-9.!#$%&'*+/=?^_`{|}~-]+ [@] @@ -85,7 +83,8 @@ extern int _scan_autolink_email(const unsigned char *p) // Try to match an HTML tag after first <, returning num of chars matched. extern int _scan_html_tag(const unsigned char *p) { - SCAN_DATA; + const unsigned char *marker = NULL; + const unsigned char *start = p; /*!re2c htmltag { return (p - start); } .? { return 0; } @@ -96,7 +95,8 @@ extern int _scan_html_tag(const unsigned char *p) // returning num of chars matched. extern int _scan_html_block_tag(const unsigned char *p) { - SCAN_DATA; + const unsigned char *marker = NULL; + const unsigned char *start = p; /*!re2c [<] [/] blocktagname (spacechar | [>]) { return (p - start); } [<] blocktagname (spacechar | [/>]) { return (p - start); } @@ -111,7 +111,8 @@ extern int _scan_html_block_tag(const unsigned char *p) // Newlines aren't ever allowed. extern int _scan_link_url(const unsigned char *p) { - SCAN_DATA; + const unsigned char *marker = NULL; + const unsigned char *start = p; /*!re2c [ \n]* [<] ([^<>\n\\\x00] | escaped_char | [\\])* [>] { return (p - start); } [ \n]* (reg_char+ | escaped_char | in_parens_nosp)* { return (p - start); } @@ -124,7 +125,8 @@ extern int _scan_link_url(const unsigned char *p) // level of internal nesting (quotes within quotes). extern int _scan_link_title(const unsigned char *p) { - SCAN_DATA; + const unsigned char *marker = NULL; + const unsigned char *start = p; /*!re2c ["] (escaped_char|[^"\x00])* ["] { return (p - start); } ['] (escaped_char|[^'\x00])* ['] { return (p - start); } @@ -136,7 +138,7 @@ extern int _scan_link_title(const unsigned char *p) // Match space characters, including newlines. extern int _scan_spacechars(const unsigned char *p) { - SCAN_DATA; + const unsigned char *start = p; \ /*!re2c [ \t\n]* { return (p - start); } . { return 0; } @@ -146,7 +148,8 @@ extern int _scan_spacechars(const unsigned char *p) // Match ATX header start. extern int _scan_atx_header_start(const unsigned char *p) { - SCAN_DATA; + const unsigned char *marker = NULL; + const unsigned char *start = p; /*!re2c [#]{1,6} ([ ]+|[\n]) { return (p - start); } .? { return 0; } @@ -157,7 +160,7 @@ extern int _scan_atx_header_start(const unsigned char *p) // 2 for level-2, 0 for no match. extern int _scan_setext_header_line(const unsigned char *p) { - SCAN_DATA; + const unsigned char *marker = NULL; /*!re2c [=]+ [ ]* [\n] { return 1; } [-]+ [ ]* [\n] { return 2; } @@ -170,7 +173,8 @@ extern int _scan_setext_header_line(const unsigned char *p) // spaces between the hyphens or asterisks." extern int _scan_hrule(const unsigned char *p) { - SCAN_DATA; + const unsigned char *marker = NULL; + const unsigned char *start = p; /*!re2c ([*][ ]*){3,} [ \t]* [\n] { return (p - start); } ([_][ ]*){3,} [ \t]* [\n] { return (p - start); } @@ -182,7 +186,8 @@ extern int _scan_hrule(const unsigned char *p) // Scan an opening code fence. extern int _scan_open_code_fence(const unsigned char *p) { - SCAN_DATA; + const unsigned char *marker = NULL; + const unsigned char *start = p; /*!re2c [`]{3,} / [^`\n\x00]*[\n] { return (p - start); } [~]{3,} / [^~\n\x00]*[\n] { return (p - start); } @@ -193,7 +198,8 @@ extern int _scan_open_code_fence(const unsigned char *p) // Scan a closing code fence with length at least len. extern int _scan_close_code_fence(const unsigned char *p) { - SCAN_DATA; + const unsigned char *marker = NULL; + const unsigned char *start = p; /*!re2c ([`]{3,} | [~]{3,}) / spacechar* [\n] { return (p - start); } .? { return 0; } @@ -204,7 +210,8 @@ extern int _scan_close_code_fence(const unsigned char *p) // Returns number of chars matched. extern int _scan_entity(const unsigned char *p) { - SCAN_DATA; + const unsigned char *marker = NULL; + const unsigned char *start = p; /*!re2c [&] ([#] ([Xx][A-Fa-f0-9]{1,8}|[0-9]{1,8}) |[A-Za-z][A-Za-z0-9]{1,31} ) [;] { return (p - start); } -- cgit v1.2.3 From 61e3e606e64221eaa5cf3d83dc598d5a42818d10 Mon Sep 17 00:00:00 2001 From: Vicent Marti Date: Sat, 6 Sep 2014 20:48:05 +0200 Subject: UTF8-aware detabbing and entity handling --- Makefile | 13 ++++++----- src/blocks.c | 35 ++++++------------------------ src/html/houdini.h | 2 ++ src/html/html.c | 1 - src/inlines.c | 63 ++++++++++++++++++++++-------------------------------- src/print.c | 5 ----- src/stmd.h | 3 --- src/utf8.c | 59 ++++++++++++++++++++++++++++++++++++++++++++------ 8 files changed, 95 insertions(+), 86 deletions(-) (limited to 'Makefile') diff --git a/Makefile b/Makefile index 0d2eb8b..b5e487d 100644 --- a/Makefile +++ b/Makefile @@ -1,5 +1,5 @@ -CFLAGS=-g -O3 -Wall -Wextra -std=c99 -Isrc $(OPTFLAGS) -LDFLAGS=-g -O3 -Wall -Werror +CFLAGS=-g -pg -O3 -Wall -Wextra -std=c99 -Isrc $(OPTFLAGS) +LDFLAGS=-g -pg -O3 -Wall -Werror SRCDIR=src DATADIR=data @@ -41,11 +41,11 @@ testjs: spec.txt benchjs: node js/bench.js ${BENCHINP} -HTML_OBJ=$(SRCDIR)/html/html.o $(SRCDIR)/html/houdini_href_e.o $(SRCDIR)/html/houdini_html_e.o +HTML_OBJ=$(SRCDIR)/html/html.o $(SRCDIR)/html/houdini_href_e.o $(SRCDIR)/html/houdini_html_e.o $(SRCDIR)/html/houdini_html_u.o STMD_OBJ=$(SRCDIR)/inlines.o $(SRCDIR)/buffer.o $(SRCDIR)/blocks.o $(SRCDIR)/scanners.c $(SRCDIR)/print.o $(SRCDIR)/utf8.o -$(PROG): $(SRCDIR)/main.c $(HTML_OBJ) $(STMD_OBJ) - $(CC) $(LDFLAGS) -o $@ $^ +$(PROG): $(SRCDIR)/html/html_unescape.h $(SRCDIR)/case_fold_switch.inc $(HTML_OBJ) $(STMD_OBJ) $(SRCDIR)/main.c + $(CC) $(LDFLAGS) -o $@ $(HTML_OBJ) $(STMD_OBJ) $(SRCDIR)/main.c $(SRCDIR)/scanners.c: $(SRCDIR)/scanners.re re2c --case-insensitive -bis $< > $@ || (rm $@ && false) @@ -53,6 +53,9 @@ $(SRCDIR)/scanners.c: $(SRCDIR)/scanners.re $(SRCDIR)/case_fold_switch.inc: $(DATADIR)/CaseFolding-3.2.0.txt perl mkcasefold.pl < $< > $@ +$(SRCDIR)/html/html_unescape.h: $(SRCDIR)/html/html_unescape.gperf + gperf -I -t -N find_entity -H hash_entity -K entity -C -l --null-strings -m5 $< > $@ + .PHONY: leakcheck clean fuzztest dingus upload dingus: diff --git a/src/blocks.c b/src/blocks.c index f671b5e..8c7d49c 100644 --- a/src/blocks.c +++ b/src/blocks.c @@ -5,6 +5,8 @@ #include #include "stmd.h" +#include "utf8.h" +#include "html/houdini.h" #include "scanners.h" #include "uthash.h" @@ -184,7 +186,7 @@ static void finalize(node_block* b, int line_number) firstlinelen = strbuf_strchr(&b->string_content, '\n', 0); strbuf_init(&b->attributes.fenced_code_data.info, 0); - strbuf_set( + houdini_unescape_html_f( &b->attributes.fenced_code_data.info, b->string_content.ptr, firstlinelen @@ -369,31 +371,6 @@ static int lists_match(struct ListData list_data, list_data.bullet_char == item_data.bullet_char); } -static void expand_tabs(strbuf *ob, const unsigned char *line, size_t size) -{ - size_t i = 0, tab = 0; - - while (i < size) { - size_t org = i; - - while (i < size && line[i] != '\t') { - i++; tab++; - } - - if (i > org) - strbuf_put(ob, line + org, i - org); - - if (i >= size) - break; - - do { - strbuf_putc(ob, ' '); tab++; - } while (tab % 4); - - i++; - } -} - static node_block *finalize_document(node_block *document, int linenum) { while (document != document->top) { @@ -415,7 +392,7 @@ extern node_block *stmd_parse_file(FILE *f) node_block *document = make_document(); while (fgets((char *)buffer, sizeof(buffer), f)) { - expand_tabs(&line, buffer, strlen((char *)buffer)); + utf8proc_detab(&line, buffer, strlen((char *)buffer)); incorporate_line(&line, linenum, &document); strbuf_clear(&line); linenum++; @@ -436,10 +413,10 @@ extern node_block *stmd_parse_document(const unsigned char *buffer, size_t len) const unsigned char *eol = memchr(buffer, '\n', end - buffer); if (!eol) { - expand_tabs(&line, buffer, end - buffer); + utf8proc_detab(&line, buffer, end - buffer); buffer = end; } else { - expand_tabs(&line, buffer, (eol - buffer) + 1); + utf8proc_detab(&line, buffer, (eol - buffer) + 1); buffer += (eol - buffer) + 1; } diff --git a/src/html/houdini.h b/src/html/houdini.h index 1e54d20..5fd690d 100644 --- a/src/html/houdini.h +++ b/src/html/houdini.h @@ -25,9 +25,11 @@ extern "C" { #define HOUDINI_ESCAPED_SIZE(x) (((x) * 12) / 10) #define HOUDINI_UNESCAPED_SIZE(x) (x) +extern size_t houdini_unescape_ent(strbuf *ob, const uint8_t *src, size_t size); extern int houdini_escape_html(strbuf *ob, const uint8_t *src, size_t size); extern int houdini_escape_html0(strbuf *ob, const uint8_t *src, size_t size, int secure); extern int houdini_unescape_html(strbuf *ob, const uint8_t *src, size_t size); +extern void houdini_unescape_html_f(strbuf *ob, const uint8_t *src, size_t size); extern int houdini_escape_xml(strbuf *ob, const uint8_t *src, size_t size); extern int houdini_escape_uri(strbuf *ob, const uint8_t *src, size_t size); extern int houdini_escape_url(strbuf *ob, const uint8_t *src, size_t size); diff --git a/src/html/html.c b/src/html/html.c index 758ec80..595dfcd 100644 --- a/src/html/html.c +++ b/src/html/html.c @@ -166,7 +166,6 @@ void inlines_to_html(strbuf *html, node_inl* ils) break; case INL_RAW_HTML: - case INL_ENTITY: strbuf_put(html, ils->content.literal.data, ils->content.literal.len); diff --git a/src/inlines.c b/src/inlines.c index 6b17027..7b27150 100644 --- a/src/inlines.c +++ b/src/inlines.c @@ -5,6 +5,8 @@ #include #include "stmd.h" +#include "html/houdini.h" +#include "utf8.h" #include "uthash.h" #include "scanners.h" @@ -176,7 +178,6 @@ inline static node_inl* make_simple(int t) #define make_str(s) make_literal(INL_STRING, s) #define make_code(s) make_literal(INL_CODE, s) #define make_raw_html(s) make_literal(INL_RAW_HTML, s) -#define make_entity(s) make_literal(INL_ENTITY, s) #define make_linebreak() make_simple(INL_LINEBREAK) #define make_softbreak() make_simple(INL_SOFTBREAK) #define make_emph(contents) make_inlines(INL_EMPH, contents) @@ -191,7 +192,6 @@ extern void free_inlines(node_inl* e) case INL_STRING: case INL_RAW_HTML: case INL_CODE: - case INL_ENTITY: chunk_free(&e->content.literal); break; case INL_LINEBREAK: @@ -540,45 +540,34 @@ static node_inl* handle_backslash(subject *subj) // Assumes the subject has an '&' character at the current position. static node_inl* handle_entity(subject* subj) { - int match; - node_inl *result; - match = scan_entity(&subj->input, subj->pos); - if (match) { - result = make_entity(chunk_dup(&subj->input, subj->pos, match)); - subj->pos += match; - } else { - advance(subj); - result = make_str(chunk_literal("&")); - } - return result; + strbuf ent = GH_BUF_INIT; + size_t len; + + advance(subj); + + len = houdini_unescape_ent(&ent, + subj->input.data + subj->pos, + subj->input.len - subj->pos + ); + + if (len == 0) + return make_str(chunk_literal("&")); + + subj->pos += len; + return make_str(chunk_buf_detach(&ent)); } // Like make_str, but parses entities. // Returns an inline sequence consisting of str and entity elements. static node_inl *make_str_with_entities(chunk *content) { - node_inl *result = NULL; - node_inl *new; - int searchpos; - char c; - subject subj; - - subject_from_chunk(&subj, content, NULL); + strbuf unescaped = GH_BUF_INIT; - while ((c = peek_char(&subj))) { - switch (c) { - case '&': - new = handle_entity(&subj); - break; - default: - searchpos = chunk_strchr(&subj.input, '&', subj.pos); - new = make_str(chunk_dup(&subj.input, subj.pos, searchpos - subj.pos)); - subj.pos = searchpos; - } - result = append_inlines(result, new); + if (houdini_unescape_html(&unescaped, content->data, (size_t)content->len)) { + return make_str(chunk_buf_detach(&unescaped)); + } else { + return make_str(*content); } - - return result; } // Destructively unescape a string: remove backslashes before punctuation chars. @@ -611,9 +600,9 @@ static unsigned char *clean_url(chunk *url, int is_email) strbuf_puts(&buf, "mailto:"); if (url->data[0] == '<' && url->data[url->len - 1] == '>') { - strbuf_put(&buf, url->data + 1, url->len - 2); + houdini_unescape_html_f(&buf, url->data + 1, url->len - 2); } else { - strbuf_put(&buf, url->data, url->len); + houdini_unescape_html_f(&buf, url->data, url->len); } unescape_buffer(&buf); @@ -636,9 +625,9 @@ static unsigned char *clean_title(chunk *title) if ((first == '\'' && last == '\'') || (first == '(' && last == ')') || (first == '"' && last == '"')) { - strbuf_set(&buf, title->data + 1, title->len - 2); + houdini_unescape_html_f(&buf, title->data + 1, title->len - 2); } else { - strbuf_set(&buf, title->data, title->len); + houdini_unescape_html_f(&buf, title->data, title->len); } unescape_buffer(&buf); diff --git a/src/print.c b/src/print.c index 0ff86fa..9240dac 100644 --- a/src/print.c +++ b/src/print.c @@ -145,11 +145,6 @@ extern void print_inlines(node_inl* ils, int indent) print_str(ils->content.literal.data, ils->content.literal.len); putchar('\n'); break; - case INL_ENTITY: - printf("entity "); - print_str(ils->content.literal.data, ils->content.literal.len); - putchar('\n'); - break; case INL_LINK: case INL_IMAGE: printf("%s url=", ils->tag == INL_LINK ? "link" : "image"); diff --git a/src/stmd.h b/src/stmd.h index be65371..c80eeda 100644 --- a/src/stmd.h +++ b/src/stmd.h @@ -17,7 +17,6 @@ struct node_inl { INL_LINEBREAK, INL_CODE, INL_RAW_HTML, - INL_ENTITY, INL_EMPH, INL_STRONG, INL_LINK, @@ -133,6 +132,4 @@ void print_blocks(node_block* blk, int indent); void blocks_to_html(strbuf *html, node_block *b, bool tight); void inlines_to_html(strbuf *html, node_inl *b); -void utf8proc_case_fold(strbuf *dest, const unsigned char *str, int len); - #endif diff --git a/src/utf8.c b/src/utf8.c index cebd872..12d7ba5 100644 --- a/src/utf8.c +++ b/src/utf8.c @@ -3,7 +3,7 @@ #include #include -#include "stmd.h" +#include "utf8.h" static const int8_t utf8proc_utf8class[256] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, @@ -23,6 +23,12 @@ static const int8_t utf8proc_utf8class[256] = { 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 0, 0, 0, 0, 0, 0, 0, 0 }; +static void encode_unknown(strbuf *buf) +{ + static const unsigned char repl[] = {239, 191, 189}; + strbuf_put(buf, repl, 3); +} + ssize_t utf8proc_charlen(const uint8_t *str, ssize_t str_len) { ssize_t length, i; @@ -46,6 +52,46 @@ ssize_t utf8proc_charlen(const uint8_t *str, ssize_t str_len) return length; } +void utf8proc_detab(strbuf *ob, const unsigned char *line, size_t size) +{ + static const unsigned char whitespace[] = " "; + + size_t i = 0, tab = 0; + + while (i < size) { + size_t org = i; + + while (i < size && line[i] != '\t' && line[i] <= 0x80) { + i++; tab++; + } + + if (i > org) + strbuf_put(ob, line + org, i - org); + + if (i >= size) + break; + + if (line[i] == '\t') { + int numspaces = 4 - (tab % 4); + strbuf_put(ob, whitespace, numspaces); + i += 1; + tab += numspaces; + } else { + ssize_t charlen = utf8proc_charlen(line + i, size - i); + + if (charlen < 0) { + encode_unknown(ob); + i++; + } else { + strbuf_put(ob, line + i, charlen); + i += charlen; + } + + tab += 1; + } + } +} + ssize_t utf8proc_iterate(const uint8_t *str, ssize_t str_len, int32_t *dst) { ssize_t length; @@ -89,9 +135,9 @@ void utf8proc_encode_char(int32_t uc, strbuf *buf) unsigned char dst[4]; int len = 0; - if (uc < 0x00) { - assert(false); - } else if (uc < 0x80) { + assert(uc >= 0); + + if (uc < 0x80) { dst[0] = uc; len = 1; } else if (uc < 0x800) { @@ -116,7 +162,8 @@ void utf8proc_encode_char(int32_t uc, strbuf *buf) dst[3] = 0x80 + (uc & 0x3F); len = 4; } else { - assert(false); + encode_unknown(buf); + return; } strbuf_put(buf, dst, len); @@ -133,7 +180,7 @@ void utf8proc_case_fold(strbuf *dest, const unsigned char *str, int len) ssize_t char_len = utf8proc_iterate(str, len, &c); if (char_len < 0) { - bufpush(0xFFFD); + encode_unknown(dest); continue; } -- cgit v1.2.3 From 9d86d2f32303ae0048f6a5daa552bacceb9b12ea Mon Sep 17 00:00:00 2001 From: Vicent Marti Date: Tue, 9 Sep 2014 04:00:36 +0200 Subject: Update the spec with better entity handling --- Makefile | 4 ++-- spec.txt | 22 ++++++++++++---------- src/html/houdini_html_u.c | 2 +- 3 files changed, 15 insertions(+), 13 deletions(-) (limited to 'Makefile') diff --git a/Makefile b/Makefile index b5e487d..5d13272 100644 --- a/Makefile +++ b/Makefile @@ -1,5 +1,5 @@ -CFLAGS=-g -pg -O3 -Wall -Wextra -std=c99 -Isrc $(OPTFLAGS) -LDFLAGS=-g -pg -O3 -Wall -Werror +CFLAGS=-g -O3 -Wall -Wextra -std=c99 -Isrc $(OPTFLAGS) +LDFLAGS=-g -O3 -Wall -Werror SRCDIR=src DATADIR=data diff --git a/spec.txt b/spec.txt index ebd6d98..112dccc 100644 --- a/spec.txt +++ b/spec.txt @@ -3762,20 +3762,20 @@ as the "unknown codepoint" character (`0xFFFD`) [Hexadecimal entities](#hexadecimal-entities) consist of `&#` + either `X` or `x` + a string of 1-8 hexadecimal digits -+ `;`. ++ `;`. They will also be parsed and turned into their corresponding UTF8 values in the AST. . - " ആ ಫ +" ആ ಫ . -

     " ആ ಫ

    +

    " ആ ಫ

    . Here are some nonentities: . -  &x; &#; &#x; � &ThisIsWayTooLongToBeAnEntityIsntIt; &hi?; +  &x; &#; &#x; &ThisIsWayTooLongToBeAnEntityIsntIt; &hi?; . -

    &nbsp &x; &#; &#x; &#123456789; &ThisIsWayTooLongToBeAnEntityIsntIt; &hi?;

    +

    &nbsp &x; &#; &#x; &ThisIsWayTooLongToBeAnEntityIsntIt; &hi?;

    . Although HTML5 does accept some entities without a trailing semicolon @@ -3808,7 +3808,7 @@ code blocks, including raw HTML, URLs, [link titles](#link-title), and . [foo](/föö "föö") . -

    foo

    +

    foo

    . . @@ -3816,7 +3816,7 @@ code blocks, including raw HTML, URLs, [link titles](#link-title), and [foo]: /föö "föö" . -

    foo

    +

    foo

    . . @@ -3824,7 +3824,7 @@ code blocks, including raw HTML, URLs, [link titles](#link-title), and foo ``` . -
    foo
+
    foo
 
    
 .
 
@@ -4817,12 +4817,14 @@ in Markdown:
 
    link
    
 .
 
-URL-escaping and entities should be left alone inside the destination:
+URL-escaping and should be left alone inside the destination, as all URL-escaped characters
+are also valid URL characters. HTML entities in the destination will be parsed into their UTF8
+codepoints, as usual, and optionally URL-escaped when written as HTML.
 
 .
 [link](foo%20bä)
 .
-
    link
    
+
    link
    
 .
 
 Note that, because titles can often be parsed as destinations,
diff --git a/src/html/houdini_html_u.c b/src/html/houdini_html_u.c
index 762f980..b8e2d8d 100644
--- a/src/html/houdini_html_u.c
+++ b/src/html/houdini_html_u.c
@@ -24,7 +24,7 @@ houdini_unescape_ent(strbuf *ob, const uint8_t *src, size_t size)
 				codepoint = (codepoint * 16) + ((src[i] | 32) % 39 - 9);
 		}
 
-		if (i < size && src[i] == ';') {
+		if (i < size && src[i] == ';' && codepoint) {
 			utf8proc_encode_char(codepoint, ob);
 			return i + 1;
 		}
-- 
cgit v1.2.3


From 94a79a605f3e76a43f1f87a5044f6761b99e5ca5 Mon Sep 17 00:00:00 2001
From: Vicent Marti 
Date: Wed, 10 Sep 2014 18:33:27 +0200
Subject: Cleanup reference implementation

---
 Makefile         |   2 +-
 src/blocks.c     |  16 ++---
 src/buffer.c     |  43 ++++++++++++++
 src/buffer.h     |   2 +
 src/inlines.c    | 176 +++++++------------------------------------------------
 src/references.c | 109 ++++++++++++++++++++++++++++++++++
 src/references.h |  27 +++++++++
 src/stmd.h       |  26 +++-----
 src/utf8.c       |  10 ++--
 src/utf8.h       |   5 +-
 10 files changed, 225 insertions(+), 191 deletions(-)
 create mode 100644 src/references.c
 create mode 100644 src/references.h

(limited to 'Makefile')

diff --git a/Makefile b/Makefile
index 5d13272..11e2141 100644
--- a/Makefile
+++ b/Makefile
@@ -42,7 +42,7 @@ benchjs:
 	node js/bench.js ${BENCHINP}
 
 HTML_OBJ=$(SRCDIR)/html/html.o $(SRCDIR)/html/houdini_href_e.o $(SRCDIR)/html/houdini_html_e.o $(SRCDIR)/html/houdini_html_u.o
-STMD_OBJ=$(SRCDIR)/inlines.o $(SRCDIR)/buffer.o $(SRCDIR)/blocks.o $(SRCDIR)/scanners.c $(SRCDIR)/print.o $(SRCDIR)/utf8.o
+STMD_OBJ=$(SRCDIR)/inlines.o $(SRCDIR)/buffer.o $(SRCDIR)/blocks.o $(SRCDIR)/scanners.c $(SRCDIR)/print.o $(SRCDIR)/utf8.o $(SRCDIR)/references.c
 
 $(PROG): $(SRCDIR)/html/html_unescape.h $(SRCDIR)/case_fold_switch.inc $(HTML_OBJ) $(STMD_OBJ) $(SRCDIR)/main.c
 	$(CC) $(LDFLAGS) -o $@ $(HTML_OBJ) $(STMD_OBJ) $(SRCDIR)/main.c
diff --git a/src/blocks.c b/src/blocks.c
index 72b2dc2..30a8284 100644
--- a/src/blocks.c
+++ b/src/blocks.c
@@ -8,7 +8,6 @@
 #include "utf8.h"
 #include "html/houdini.h"
 #include "scanners.h"
-#include "uthash.h"
 
 #define peek_at(i, n) (i)->data[n]
 
@@ -36,12 +35,7 @@ static node_block* make_block(int tag, int start_line, int start_column)
 extern node_block* make_document()
 {
 	node_block *e = make_block(BLOCK_DOCUMENT, 1, 1);
-	reference *map = NULL;
-	reference ** refmap;
-
-	refmap = (reference**) malloc(sizeof(reference*));
-	*refmap = map;
-	e->as.document.refmap = refmap;
+	e->as.document.refmap = reference_map_new();
 	e->top = e;
 
 	return e;
@@ -164,7 +158,7 @@ static void finalize(node_block* b, int line_number)
 		case BLOCK_PARAGRAPH:
 			pos = 0;
 			while (strbuf_at(&b->string_content, 0) == '[' &&
-					(pos = parse_reference(&b->string_content, b->top->as.document.refmap))) {
+					(pos = parse_reference_inline(&b->string_content, b->top->as.document.refmap))) {
 
 				strbuf_drop(&b->string_content, pos);
 			}
@@ -192,7 +186,7 @@ static void finalize(node_block* b, int line_number)
 			strbuf_drop(&b->string_content, firstlinelen + 1);
 
 			strbuf_trim(&b->as.code.info);
-			unescape_buffer(&b->as.code.info);
+			strbuf_unescape(&b->as.code.info);
 			break;
 
 		case BLOCK_LIST: // determine tight/loose status
@@ -268,7 +262,7 @@ extern void free_blocks(node_block* e)
 		if (e->tag == BLOCK_FENCED_CODE) {
 			strbuf_free(&e->as.code.info);
 		} else if (e->tag == BLOCK_DOCUMENT) {
-			free_reference_map(e->as.document.refmap);
+			reference_map_free(e->as.document.refmap);
 		}
 		free_blocks(e->children);
 		free(e);
@@ -278,7 +272,7 @@ extern void free_blocks(node_block* e)
 
 // Walk through node_block and all children, recursively, parsing
 // string content into inline content where appropriate.
-void process_inlines(node_block* cur, reference** refmap)
+void process_inlines(node_block* cur, reference_map *refmap)
 {
 	switch (cur->tag) {
 		case BLOCK_PARAGRAPH:
diff --git a/src/buffer.c b/src/buffer.c
index 90c2186..cdf8ca0 100644
--- a/src/buffer.c
+++ b/src/buffer.c
@@ -308,3 +308,46 @@ void strbuf_trim(strbuf *buf)
 
 	buf->ptr[buf->size] = '\0';
 }
+
+// Destructively modify string, collapsing consecutive
+// space and newline characters into a single space.
+void strbuf_normalize_whitespace(strbuf *s)
+{
+	bool last_char_was_space = false;
+	int r, w;
+
+	for (r = 0, w = 0; r < s->size; ++r) {
+		switch (s->ptr[r]) {
+		case ' ':
+		case '\n':
+			if (last_char_was_space)
+				break;
+
+			s->ptr[w++] = ' ';
+			last_char_was_space = true;
+			break;
+
+		default:
+			s->ptr[w++] = s->ptr[r];
+			last_char_was_space = false;
+		}
+	}
+
+	strbuf_truncate(s, w);
+}
+
+// Destructively unescape a string: remove backslashes before punctuation chars.
+extern void strbuf_unescape(strbuf *buf)
+{
+	int r, w;
+
+	for (r = 0, w = 0; r < buf->size; ++r) {
+		if (buf->ptr[r] == '\\' && ispunct(buf->ptr[r + 1]))
+			continue;
+
+		buf->ptr[w++] = buf->ptr[r];
+	}
+
+	strbuf_truncate(buf, w);
+}
+
diff --git a/src/buffer.h b/src/buffer.h
index 6f45cbb..1bc1eee 100644
--- a/src/buffer.h
+++ b/src/buffer.h
@@ -108,5 +108,7 @@ int strbuf_strrchr(const strbuf *buf, int c, int pos);
 void strbuf_drop(strbuf *buf, int n);
 void strbuf_truncate(strbuf *buf, int len);
 void strbuf_trim(strbuf *buf);
+void strbuf_normalize_whitespace(strbuf *s);
+void strbuf_unescape(strbuf *s);
 
 #endif
diff --git a/src/inlines.c b/src/inlines.c
index aa0e13e..3040f09 100644
--- a/src/inlines.c
+++ b/src/inlines.c
@@ -7,110 +7,23 @@
 #include "stmd.h"
 #include "html/houdini.h"
 #include "utf8.h"
-#include "uthash.h"
 #include "scanners.h"
 
 typedef struct Subject {
 	chunk input;
 	int pos;
-	int            label_nestlevel;
-	reference**    reference_map;
+	int label_nestlevel;
+	reference_map *refmap;
 } subject;
 
-reference* lookup_reference(reference** refmap, chunk *label);
-reference* make_reference(chunk *label, chunk *url, chunk *title);
-
-static unsigned char *clean_url(chunk *url);
-static unsigned char *clean_title(chunk *title);
-static unsigned char *clean_autolink(chunk *url, int is_email);
-
-inline static void chunk_free(chunk *c);
-inline static void chunk_trim(chunk *c);
-
-inline static chunk chunk_literal(const char *data);
-inline static chunk chunk_buf_detach(strbuf *buf);
-inline static chunk chunk_dup(const chunk *ch, int pos, int len);
-
-static node_inl *parse_chunk_inlines(chunk *chunk, reference** refmap);
+static node_inl *parse_chunk_inlines(chunk *chunk, reference_map *refmap);
 static node_inl *parse_inlines_while(subject* subj, int (*f)(subject*));
 static int parse_inline(subject* subj, node_inl ** last);
 
-static void subject_from_chunk(subject *e, chunk *chunk, reference** refmap);
-static void subject_from_buf(subject *e, strbuf *buffer, reference** refmap);
+static void subject_from_chunk(subject *e, chunk *chunk, reference_map *refmap);
+static void subject_from_buf(subject *e, strbuf *buffer, reference_map *refmap);
 static int subject_find_special_char(subject *subj);
 
-static void normalize_whitespace(strbuf *s);
-
-extern void free_reference(reference *ref) {
-	free(ref->label);
-	free(ref->url);
-	free(ref->title);
-	free(ref);
-}
-
-extern void free_reference_map(reference **refmap) {
-	/* free the hash table contents */
-	reference *s;
-	reference *tmp;
-	if (refmap != NULL) {
-		HASH_ITER(hh, *refmap, s, tmp) {
-			HASH_DEL(*refmap, s);
-			free_reference(s);
-		}
-		free(refmap);
-	}
-}
-
-// normalize reference:  collapse internal whitespace to single space,
-// remove leading/trailing whitespace, case fold
-static unsigned char *normalize_reference(chunk *ref)
-{
-	strbuf normalized = GH_BUF_INIT;
-
-	utf8proc_case_fold(&normalized, ref->data, ref->len);
-	strbuf_trim(&normalized);
-	normalize_whitespace(&normalized);
-
-	return strbuf_detach(&normalized);
-}
-
-// Returns reference if refmap contains a reference with matching
-// label, otherwise NULL.
-extern reference* lookup_reference(reference** refmap, chunk *label)
-{
-	reference *ref = NULL;
-	unsigned char *norm = normalize_reference(label);
-	if (refmap != NULL) {
-		HASH_FIND_STR(*refmap, (char*)norm, ref);
-	}
-	free(norm);
-	return ref;
-}
-
-extern reference* make_reference(chunk *label, chunk *url, chunk *title)
-{
-	reference *ref;
-	ref = malloc(sizeof(reference));
-	ref->label = normalize_reference(label);
-	ref->url = clean_url(url);
-	ref->title = clean_title(title);
-	return ref;
-}
-
-extern void add_reference(reference** refmap, reference* ref)
-{
-	reference * t = NULL;
-	const char *label = (const char *)ref->label;
-
-	HASH_FIND(hh, *refmap, label, strlen(label), t);
-
-	if (t == NULL) {
-		HASH_ADD_KEYPTR(hh, *refmap, label, strlen(label), ref);
-	} else {
-		free_reference(ref);  // we free this now since it won't be in the refmap
-	}
-}
-
 static unsigned char *bufdup(const unsigned char *buf)
 {
 	unsigned char *new = NULL;
@@ -236,26 +149,26 @@ inline static node_inl* append_inlines(node_inl* a, node_inl* b)
 	return a;
 }
 
-static void subject_from_buf(subject *e, strbuf *buffer, reference** refmap)
+static void subject_from_buf(subject *e, strbuf *buffer, reference_map *refmap)
 {
 	e->input.data = buffer->ptr;
 	e->input.len = buffer->size;
 	e->input.alloc = 0;
 	e->pos = 0;
 	e->label_nestlevel = 0;
-	e->reference_map = refmap;
+	e->refmap = refmap;
 
 	chunk_rtrim(&e->input);
 }
 
-static void subject_from_chunk(subject *e, chunk *chunk, reference** refmap)
+static void subject_from_chunk(subject *e, chunk *chunk, reference_map *refmap)
 {
 	e->input.data = chunk->data;
 	e->input.len = chunk->len;
 	e->input.alloc = 0;
 	e->pos = 0;
 	e->label_nestlevel = 0;
-	e->reference_map = refmap;
+	e->refmap = refmap;
 
 	chunk_rtrim(&e->input);
 }
@@ -325,33 +238,6 @@ static int scan_to_closing_backticks(subject* subj, int openticklength)
 	return (subj->pos);
 }
 
-// Destructively modify string, collapsing consecutive
-// space and newline characters into a single space.
-static void normalize_whitespace(strbuf *s)
-{
-	bool last_char_was_space = false;
-	int r, w;
-
-	for (r = 0, w = 0; r < s->size; ++r) {
-		switch (s->ptr[r]) {
-		case ' ':
-		case '\n':
-			if (last_char_was_space)
-				break;
-
-			s->ptr[w++] = ' ';
-			last_char_was_space = true;
-			break;
-
-		default:
-			s->ptr[w++] = s->ptr[r];
-			last_char_was_space = false;
-		}
-	}
-
-	strbuf_truncate(s, w);
-}
-
 // Parse backtick code section or raw backticks, return an inline.
 // Assumes that the subject has a backtick at the current position.
 static node_inl* handle_backticks(subject *subj)
@@ -368,7 +254,7 @@ static node_inl* handle_backticks(subject *subj)
 
 		strbuf_set(&buf, subj->input.data + startpos, endpos - startpos - openticks.len);
 		strbuf_trim(&buf);
-		normalize_whitespace(&buf);
+		strbuf_normalize_whitespace(&buf);
 
 		return make_code(chunk_buf_detach(&buf));
 	}
@@ -575,24 +461,9 @@ static node_inl *make_str_with_entities(chunk *content)
 	}
 }
 
-// Destructively unescape a string: remove backslashes before punctuation chars.
-extern void unescape_buffer(strbuf *buf)
-{
-	int r, w;
-
-	for (r = 0, w = 0; r < buf->size; ++r) {
-		if (buf->ptr[r] == '\\' && ispunct(buf->ptr[r + 1]))
-			continue;
-
-		buf->ptr[w++] = buf->ptr[r];
-	}
-
-	strbuf_truncate(buf, w);
-}
-
 // Clean a URL: remove surrounding whitespace and surrounding <>,
 // and remove \ that escape punctuation.
-static unsigned char *clean_url(chunk *url)
+unsigned char *clean_url(chunk *url)
 {
 	strbuf buf = GH_BUF_INIT;
 
@@ -607,11 +478,11 @@ static unsigned char *clean_url(chunk *url)
 		houdini_unescape_html_f(&buf, url->data, url->len);
 	}
 
-	unescape_buffer(&buf);
+	strbuf_unescape(&buf);
 	return strbuf_detach(&buf);
 }
 
-static unsigned char *clean_autolink(chunk *url, int is_email)
+unsigned char *clean_autolink(chunk *url, int is_email)
 {
 	strbuf buf = GH_BUF_INIT;
 
@@ -628,7 +499,7 @@ static unsigned char *clean_autolink(chunk *url, int is_email)
 }
 
 // Clean a title: remove surrounding quotes and remove \ that escape punctuation.
-static unsigned char *clean_title(chunk *title)
+unsigned char *clean_title(chunk *title)
 {
 	strbuf buf = GH_BUF_INIT;
 	unsigned char first, last;
@@ -648,7 +519,7 @@ static unsigned char *clean_title(chunk *title)
 		houdini_unescape_html_f(&buf, title->data, title->len);
 	}
 
-	unescape_buffer(&buf);
+	strbuf_unescape(&buf);
 	return strbuf_detach(&buf);
 }
 
@@ -810,7 +681,7 @@ static node_inl* handle_left_bracket(subject* subj)
 			} else {
 				// if we get here, we matched a label but didn't get further:
 				subj->pos = endlabel;
-				lab = parse_chunk_inlines(&rawlabel, subj->reference_map);
+				lab = parse_chunk_inlines(&rawlabel, subj->refmap);
 				result = append_inlines(make_str(chunk_literal("[")),
 						append_inlines(lab,
 							make_str(chunk_literal("]"))));
@@ -834,13 +705,13 @@ static node_inl* handle_left_bracket(subject* subj)
 			}
 
 			// lookup rawlabel in subject->reference_map:
-			ref = lookup_reference(subj->reference_map, &reflabel);
+			ref = reference_lookup(subj->refmap, &reflabel);
 			if (ref != NULL) { // found
 				lab = parse_chunk_inlines(&rawlabel, NULL);
 				result = make_ref_link(lab, ref);
 			} else {
 				subj->pos = endlabel;
-				lab = parse_chunk_inlines(&rawlabel, subj->reference_map);
+				lab = parse_chunk_inlines(&rawlabel, subj->refmap);
 				result = append_inlines(make_str(chunk_literal("[")),
 						append_inlines(lab, make_str(chunk_literal("]"))));
 			}
@@ -887,7 +758,7 @@ extern node_inl* parse_inlines_while(subject* subj, int (*f)(subject*))
 	return result;
 }
 
-node_inl *parse_chunk_inlines(chunk *chunk, reference** refmap)
+node_inl *parse_chunk_inlines(chunk *chunk, reference_map *refmap)
 {
 	subject subj;
 	subject_from_chunk(&subj, chunk, refmap);
@@ -987,7 +858,7 @@ static int parse_inline(subject* subj, node_inl ** last)
 	return 1;
 }
 
-extern node_inl* parse_inlines(strbuf *input, reference** refmap)
+extern node_inl* parse_inlines(strbuf *input, reference_map *refmap)
 {
 	subject subj;
 	subject_from_buf(&subj, input, refmap);
@@ -1009,7 +880,7 @@ void spnl(subject* subj)
 // Modify refmap if a reference is encountered.
 // Return 0 if no reference found, otherwise position of subject
 // after reference is parsed.
-extern int parse_reference(strbuf *input, reference** refmap)
+int parse_reference_inline(strbuf *input, reference_map *refmap)
 {
 	subject subj;
 
@@ -1019,7 +890,6 @@ extern int parse_reference(strbuf *input, reference** refmap)
 
 	int matchlen = 0;
 	int beforetitle;
-	reference *new = NULL;
 
 	subject_from_buf(&subj, input, NULL);
 
@@ -1065,9 +935,7 @@ extern int parse_reference(strbuf *input, reference** refmap)
 		return 0;
 	}
 	// insert reference into refmap
-	new = make_reference(&lab, &url, &title);
-	add_reference(refmap, new);
-
+	reference_create(refmap, &lab, &url, &title);
 	return subj.pos;
 }
 
diff --git a/src/references.c b/src/references.c
new file mode 100644
index 0000000..ff64b00
--- /dev/null
+++ b/src/references.c
@@ -0,0 +1,109 @@
+#include "stmd.h"
+#include "utf8.h"
+#include "references.h"
+
+static unsigned int
+refhash(const unsigned char *link_ref)
+{
+	unsigned int hash = 0;
+
+	while (*link_ref)
+		hash = (*link_ref++) + (hash << 6) + (hash << 16) - hash;
+
+	return hash;
+}
+
+// normalize reference:  collapse internal whitespace to single space,
+// remove leading/trailing whitespace, case fold
+static unsigned char *normalize_reference(chunk *ref)
+{
+	strbuf normalized = GH_BUF_INIT;
+
+	utf8proc_case_fold(&normalized, ref->data, ref->len);
+	strbuf_trim(&normalized);
+	strbuf_normalize_whitespace(&normalized);
+
+	return strbuf_detach(&normalized);
+}
+
+static void add_reference(reference_map *map, reference* ref)
+{
+	ref->next = map->table[ref->hash % REFMAP_SIZE];
+	map->table[ref->hash % REFMAP_SIZE] = ref;
+}
+
+extern reference *reference_create(reference_map *map, chunk *label, chunk *url, chunk *title)
+{
+	reference *ref;
+	ref = malloc(sizeof(reference));
+	ref->label = normalize_reference(label);
+	ref->hash = refhash(ref->label);
+	ref->url = clean_url(url);
+	ref->title = clean_title(title);
+	ref->next = NULL;
+
+	add_reference(map, ref);
+
+	return ref;
+}
+
+// Returns reference if refmap contains a reference with matching
+// label, otherwise NULL.
+reference* reference_lookup(reference_map *map, chunk *label)
+{
+	reference *ref = NULL;
+	unsigned char *norm;
+	unsigned int hash;
+	
+	if (map == NULL)
+		return NULL;
+	
+	norm = normalize_reference(label);
+	hash = refhash(norm);
+	ref = map->table[hash % REFMAP_SIZE];
+
+	while (ref) {
+		if (ref->label[0] == norm[0] &&
+			!strcmp((char *)ref->label, (char *)norm))
+			break;
+		ref = ref->next;
+	}
+
+	free(norm);
+	return ref;
+}
+
+static void reference_free(reference *ref)
+{
+	free(ref->label);
+	free(ref->url);
+	free(ref->title);
+	free(ref);
+}
+
+void reference_map_free(reference_map *map)
+{
+	unsigned int i;
+
+	for (i = 0; i < REFMAP_SIZE; ++i) {
+		reference *ref = map->table[i];
+		reference *next;
+
+		while (ref) {
+			next = ref->next;
+			reference_free(ref);
+			ref = next;
+		}
+	}
+
+	free(map->table);
+	free(map);
+}
+
+reference_map *reference_map_new(void)
+{
+	reference_map *map = malloc(sizeof(reference_map));
+	memset(map, 0x0, sizeof(reference_map));
+	return map;
+}
+
diff --git a/src/references.h b/src/references.h
new file mode 100644
index 0000000..78fffe7
--- /dev/null
+++ b/src/references.h
@@ -0,0 +1,27 @@
+#ifndef _REFERENCES_H_
+#define _REFERENCES_H_
+
+#define REFMAP_SIZE 16
+
+struct reference {
+	struct reference *next;
+	unsigned char *label;
+	unsigned char *url;
+	unsigned char *title;
+	unsigned int hash;
+};
+
+typedef struct reference reference;
+
+struct reference_map {
+	reference *table[REFMAP_SIZE];
+};
+
+typedef struct reference_map reference_map;
+
+reference_map *reference_map_new(void);
+void reference_map_free(reference_map *map);
+reference* reference_lookup(reference_map *map, chunk *label);
+extern reference *reference_create(reference_map *map, chunk *label, chunk *url, chunk *title);
+
+#endif
diff --git a/src/stmd.h b/src/stmd.h
index 21a86b0..4e21e6c 100644
--- a/src/stmd.h
+++ b/src/stmd.h
@@ -5,7 +5,7 @@
 #include 
 #include "buffer.h"
 #include "chunk.h"
-#include "uthash.h"
+#include "references.h"
 
 #define VERSION "0.1"
 #define CODE_INDENT 4
@@ -36,17 +36,7 @@ struct node_inl {
 
 typedef struct node_inl node_inl;
 
-struct reference {
-  unsigned char *label;
-  unsigned char *url;
-  unsigned char *title;
-  UT_hash_handle  hh; // used by uthash
-};
-
-typedef struct reference reference;
-
 // Types for blocks
-
 struct ListData {
 	enum {
 		bullet,
@@ -104,7 +94,7 @@ struct node_block {
 			int level;
 		} header;
 		struct {
-			reference** refmap;
+			reference_map *refmap;
 		} document;
 	} as;
 
@@ -114,14 +104,10 @@ struct node_block {
 
 typedef struct node_block node_block;
 
-node_inl* parse_inlines(strbuf *input, reference** refmap);
+node_inl* parse_inlines(strbuf *input, reference_map *refmap);
 void free_inlines(node_inl* e);
 
-int parse_reference(strbuf *input, reference** refmap);
-void free_reference(reference *ref);
-void free_reference_map(reference **refmap);
-
-void add_reference(reference** refmap, reference* ref);
+int parse_reference_inline(strbuf *input, reference_map *refmap);
 void unescape_buffer(strbuf *buf);
 
 extern node_block* make_document();
@@ -138,4 +124,8 @@ void print_blocks(node_block* blk, int indent);
 void blocks_to_html(strbuf *html, node_block *b, bool tight);
 void inlines_to_html(strbuf *html, node_inl *b);
 
+unsigned char *clean_url(chunk *url);
+unsigned char *clean_autolink(chunk *url, int is_email);
+unsigned char *clean_title(chunk *title);
+
 #endif
diff --git a/src/utf8.c b/src/utf8.c
index 12d7ba5..c65aec6 100644
--- a/src/utf8.c
+++ b/src/utf8.c
@@ -25,7 +25,7 @@ static const int8_t utf8proc_utf8class[256] = {
 
 static void encode_unknown(strbuf *buf)
 {
-	static const unsigned char repl[] = {239, 191, 189};
+	static const uint8_t repl[] = {239, 191, 189};
 	strbuf_put(buf, repl, 3);
 }
 
@@ -52,9 +52,9 @@ ssize_t utf8proc_charlen(const uint8_t *str, ssize_t str_len)
 	return length;
 }
 
-void utf8proc_detab(strbuf *ob, const unsigned char *line, size_t size)
+void utf8proc_detab(strbuf *ob, const uint8_t *line, size_t size)
 {
-	static const unsigned char whitespace[] = "    ";
+	static const uint8_t whitespace[] = "    ";
 
 	size_t i = 0, tab = 0;
 
@@ -132,7 +132,7 @@ ssize_t utf8proc_iterate(const uint8_t *str, ssize_t str_len, int32_t *dst)
 
 void utf8proc_encode_char(int32_t uc, strbuf *buf)
 {
-	unsigned char dst[4];
+	uint8_t dst[4];
 	int len = 0;
 
 	assert(uc >= 0);
@@ -169,7 +169,7 @@ void utf8proc_encode_char(int32_t uc, strbuf *buf)
 	strbuf_put(buf, dst, len);
 }
 
-void utf8proc_case_fold(strbuf *dest, const unsigned char *str, int len)
+void utf8proc_case_fold(strbuf *dest, const uint8_t *str, int len)
 {
 	int32_t c;
 
diff --git a/src/utf8.h b/src/utf8.h
index 1e4e556..9506b75 100644
--- a/src/utf8.h
+++ b/src/utf8.h
@@ -1,12 +1,13 @@
 #ifndef _H_STMD_UTF8_
 #define _H_STMD_UTF8_
 
+#include 
 #include "buffer.h"
 
-void utf8proc_case_fold(strbuf *dest, const unsigned char *str, int len);
+void utf8proc_case_fold(strbuf *dest, const uint8_t *str, int len);
 void utf8proc_encode_char(int32_t uc, strbuf *buf);
 ssize_t utf8proc_iterate(const uint8_t *str, ssize_t str_len, int32_t *dst);
 ssize_t utf8proc_charlen(const uint8_t *str, ssize_t str_len);
-void utf8proc_detab(strbuf *dest, const unsigned char *line, size_t size);
+void utf8proc_detab(strbuf *dest, const uint8_t *line, size_t size);
 
 #endif
-- 
cgit v1.2.3


From e752b9776d434f63768c50e4c73c533a43529052 Mon Sep 17 00:00:00 2001
From: John MacFarlane 
Date: Wed, 24 Sep 2014 22:22:51 -0700
Subject: Makefile:  Use ?= so variables can be set on command line.

---
 Makefile | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'Makefile')

diff --git a/Makefile b/Makefile
index 11e2141..f5f408e 100644
--- a/Makefile
+++ b/Makefile
@@ -1,9 +1,9 @@
-CFLAGS=-g -O3 -Wall -Wextra -std=c99 -Isrc $(OPTFLAGS)
-LDFLAGS=-g -O3 -Wall -Werror
-SRCDIR=src
-DATADIR=data
+CFLAGS?=-g -O3 -Wall -Wextra -std=c99 -Isrc $(OPTFLAGS)
+LDFLAGS?=-g -O3 -Wall -Werror
+SRCDIR?=src
+DATADIR?=data
 
-PROG=./stmd
+PROG?=./stmd
 
 .PHONY: all oldtests test spec benchjs testjs
 all: $(SRCDIR)/case_fold_switch.inc $(PROG)
-- 
cgit v1.2.3


From c006aececef112f61dd44cad43f0596221f29700 Mon Sep 17 00:00:00 2001
From: John MacFarlane 
Date: Wed, 24 Sep 2014 22:47:47 -0700
Subject: Suppress 'missing field initializer' warnings

from gperf generated header.
---
 Makefile | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'Makefile')

diff --git a/Makefile b/Makefile
index f5f408e..671d30d 100644
--- a/Makefile
+++ b/Makefile
@@ -1,4 +1,4 @@
-CFLAGS?=-g -O3 -Wall -Wextra -std=c99 -Isrc $(OPTFLAGS)
+CFLAGS?=-g -O3 -Wall -Wextra -std=c99 -Isrc -Wno-missing-field-initializers $(OPTFLAGS)
 LDFLAGS?=-g -O3 -Wall -Werror
 SRCDIR?=src
 DATADIR?=data
@@ -42,6 +42,7 @@ benchjs:
 	node js/bench.js ${BENCHINP}
 
 HTML_OBJ=$(SRCDIR)/html/html.o $(SRCDIR)/html/houdini_href_e.o $(SRCDIR)/html/houdini_html_e.o $(SRCDIR)/html/houdini_html_u.o
+
 STMD_OBJ=$(SRCDIR)/inlines.o $(SRCDIR)/buffer.o $(SRCDIR)/blocks.o $(SRCDIR)/scanners.c $(SRCDIR)/print.o $(SRCDIR)/utf8.o $(SRCDIR)/references.c
 
 $(PROG): $(SRCDIR)/html/html_unescape.h $(SRCDIR)/case_fold_switch.inc $(HTML_OBJ) $(STMD_OBJ) $(SRCDIR)/main.c
-- 
cgit v1.2.3


From bc5b7c288d29215c585db254a203889e0dea54e2 Mon Sep 17 00:00:00 2001
From: John MacFarlane 
Date: Tue, 7 Oct 2014 22:35:19 -0700
Subject: Removed oldtests.

---
 Makefile                                           |   8 +-
 oldtests/Blockquotes/Indents.html                  |  12 -
 oldtests/Blockquotes/Indents.markdown              |   5 -
 oldtests/Blockquotes/Nesting.html                  |  32 -
 oldtests/Blockquotes/Nesting.markdown              |  22 -
 oldtests/Blockquotes/Separation.html               |  39 -
 oldtests/Blockquotes/Separation.markdown           |  29 -
 oldtests/Code/BlankLines.html                      |  33 -
 oldtests/Code/BlankLines.markdown                  |  28 -
 oldtests/Code/BlankLinesAtEnd.html                 |  14 -
 oldtests/Code/BlankLinesAtEnd.markdown             |  14 -
 oldtests/Code/FenceMatching.html                   |   8 -
 oldtests/Code/FenceMatching.markdown               |  10 -
 oldtests/Code/FencedCodeBlocks.html                |  24 -
 oldtests/Code/FencedCodeBlocks.markdown            |  35 -
 oldtests/Code/IndentedCodeBlocks.html              |  22 -
 oldtests/Code/IndentedCodeBlocks.markdown          |  22 -
 oldtests/Code/IndentedFences.html                  |  20 -
 oldtests/Code/IndentedFences.markdown              |  26 -
 oldtests/Code/IndentedInLists.html                 |  22 -
 oldtests/Code/IndentedInLists.markdown             |  17 -
 oldtests/Code/Inline.html                          |  13 -
 oldtests/Code/Inline.markdown                      |  13 -
 oldtests/Code/ListBreakAfter.html                  |  30 -
 oldtests/Code/ListBreakAfter.markdown              |  26 -
 oldtests/Code/WhiteLines.html                      |   7 -
 oldtests/Code/WhiteLines.markdown                  |   9 -
 oldtests/Emphasis/Escapes.html                     |   1 -
 oldtests/Emphasis/Escapes.markdown                 |   1 -
 oldtests/Emphasis/NestedEmphAndStrong.html         |  66 --
 oldtests/Emphasis/NestedEmphAndStrong.markdown     |  69 --
 oldtests/Emphasis/Pathological.html                |  24 -
 oldtests/Emphasis/Pathological.markdown            |  26 -
 oldtests/Emphasis/Punctuation.html                 |  10 -
 oldtests/Emphasis/Punctuation.markdown             |  19 -
 oldtests/HTML/Blocks.html                          |  18 -
 oldtests/HTML/Blocks.markdown                      |  26 -
 oldtests/HTML/Inline.html                          |   8 -
 oldtests/HTML/Inline.markdown                      |   8 -
 oldtests/HTML/UppercaseTags.html                   |   4 -
 oldtests/HTML/UppercaseTags.markdown               |   5 -
 oldtests/Headers/ATX.html                          |  14 -
 oldtests/Headers/ATX.markdown                      |  20 -
 oldtests/Headers/Setext.html                       |   9 -
 oldtests/Headers/Setext.markdown                   |  17 -
 oldtests/Links/AngleBrackets.html                  |   3 -
 oldtests/Links/AngleBrackets.markdown              |   7 -
 oldtests/Links/AutoLinks.html                      |   7 -
 oldtests/Links/AutoLinks.markdown                  |   7 -
 oldtests/Links/BackticksInLinks.html               |   1 -
 oldtests/Links/BackticksInLinks.markdown           |   1 -
 oldtests/Links/CaseInsensitiveReferences.html      |   1 -
 oldtests/Links/CaseInsensitiveReferences.markdown  |   3 -
 oldtests/Links/Entities.html                       |   2 -
 oldtests/Links/Entities.markdown                   |   3 -
 oldtests/Links/InlineLinks.html                    |  10 -
 oldtests/Links/InlineLinks.markdown                |   9 -
 oldtests/Links/ParensInURLs.html                   |   6 -
 oldtests/Links/ParensInURLs.markdown               |  14 -
 oldtests/Links/ReferenceLinks.html                 |   7 -
 oldtests/Links/ReferenceLinks.markdown             |  10 -
 oldtests/Lists/CodeBlocksInLists.html              |  14 -
 oldtests/Lists/CodeBlocksInLists.markdown          |  18 -
 oldtests/Lists/ConsecutiveLists.html               |  20 -
 oldtests/Lists/ConsecutiveLists.markdown           |  10 -
 oldtests/Lists/EmptyListItem.html                  |  10 -
 oldtests/Lists/EmptyListItem.markdown              |   7 -
 oldtests/Lists/InBlockquote.html                   |  22 -
 oldtests/Lists/InBlockquote.markdown               |  12 -
 oldtests/Lists/Indents.html                        |  22 -
 oldtests/Lists/Indents.markdown                    |  17 -
 oldtests/Lists/ListsAndHRs.html                    |   7 -
 oldtests/Lists/ListsAndHRs.markdown                |   3 -
 oldtests/Lists/ListsAndSetextHeaders.html          |   6 -
 oldtests/Lists/ListsAndSetextHeaders.markdown      |   4 -
 oldtests/Lists/MultipleBlankLines.html             |  56 --
 oldtests/Lists/MultipleBlankLines.markdown         |  37 -
 oldtests/Lists/Start.html                          |  11 -
 oldtests/Lists/Start.markdown                      |   7 -
 oldtests/Lists/Sublists.html                       |  49 --
 oldtests/Lists/Sublists.markdown                   |  24 -
 oldtests/Lists/TightAndLoose.html                  |  49 --
 oldtests/Lists/TightAndLoose.markdown              |  45 --
 oldtests/Lists/TightLooseBlockquote.html           |  32 -
 oldtests/Lists/TightLooseBlockquote.markdown       |  25 -
 oldtests/Lists/TightLooseMore.html                 |   7 -
 oldtests/Lists/TightLooseMore.markdown             |   4 -
 oldtests/Lists/TwoBlankLinesEndList.html           |  21 -
 oldtests/Lists/TwoBlankLinesEndList.markdown       |  20 -
 oldtests/Makefile                                  |  55 --
 oldtests/Misc/BackslashEscapes.html                |  14 -
 oldtests/Misc/BackslashEscapes.markdown            |  19 -
 oldtests/Misc/Laziness.html                        |  22 -
 oldtests/Misc/Laziness.markdown                    |  14 -
 oldtests/Misc/LineBreaks.html                      |  11 -
 oldtests/Misc/LineBreaks.markdown                  |  18 -
 oldtests/Misc/Transitions.html                     |  26 -
 oldtests/Misc/Transitions.markdown                 |  20 -
 oldtests/Original/Amps_and_angle_encoding.html     |   9 -
 oldtests/Original/Amps_and_angle_encoding.markdown |  21 -
 oldtests/Original/Auto_links.html                  |  13 -
 oldtests/Original/Auto_links.markdown              |  13 -
 oldtests/Original/Backslash_escapes.html           |  75 --
 oldtests/Original/Backslash_escapes.markdown       | 120 ---
 .../Original/Blockquotes_with_code_blocks.html     |  12 -
 .../Original/Blockquotes_with_code_blocks.markdown |  11 -
 oldtests/Original/Code_Blocks.html                 |  12 -
 oldtests/Original/Code_Blocks.markdown             |  14 -
 oldtests/Original/Code_Spans.html                  |   3 -
 oldtests/Original/Code_Spans.markdown              |   5 -
 oldtests/Original/Horizontal_rules.html            |  39 -
 oldtests/Original/Horizontal_rules.markdown        |  67 --
 oldtests/Original/Images.html                      |  11 -
 oldtests/Original/Images.markdown                  |  26 -
 oldtests/Original/Inline_HTML_Advanced.html        |  23 -
 oldtests/Original/Inline_HTML_Advanced.markdown    |  30 -
 oldtests/Original/Inline_HTML_Simple.html          |  45 --
 oldtests/Original/Inline_HTML_Simple.markdown      |  69 --
 oldtests/Original/Inline_HTML_comments.html        |   8 -
 oldtests/Original/Inline_HTML_comments.markdown    |  13 -
 oldtests/Original/Links_inline_style.html          |  12 -
 oldtests/Original/Links_inline_style.markdown      |  24 -
 oldtests/Original/Links_reference_style.html       |  28 -
 oldtests/Original/Links_reference_style.markdown   |  71 --
 oldtests/Original/Links_shortcut_references.html   |   6 -
 .../Original/Links_shortcut_references.markdown    |  20 -
 oldtests/Original/Literal_quotes_in_titles.html    |   2 -
 .../Original/Literal_quotes_in_titles.markdown     |   7 -
 .../Original/Markdown_Documentation_Basics.html    | 242 ------
 .../Markdown_Documentation_Basics.markdown         | 306 -------
 .../Original/Markdown_Documentation_Syntax.html    | 708 ----------------
 .../Markdown_Documentation_Syntax.markdown         | 888 ---------------------
 oldtests/Original/Nested_blockquotes.html          |   7 -
 oldtests/Original/Nested_blockquotes.markdown      |   5 -
 oldtests/Original/Ordered_and_unordered_lists.html | 112 ---
 .../Original/Ordered_and_unordered_lists.markdown  | 131 ---
 oldtests/Original/README                           |  15 -
 oldtests/Original/Strong_and_em_together.html      |   4 -
 oldtests/Original/Strong_and_em_together.markdown  |   7 -
 oldtests/Original/Tabs.html                        |  19 -
 oldtests/Original/Tabs.markdown                    |  21 -
 oldtests/Original/Tidyness.html                    |   8 -
 oldtests/Original/Tidyness.markdown                |   5 -
 oldtests/Tabs/TabConversionUnicode.html            |   1 -
 oldtests/Tabs/TabConversionUnicode.markdown        |   1 -
 145 files changed, 3 insertions(+), 5020 deletions(-)
 delete mode 100644 oldtests/Blockquotes/Indents.html
 delete mode 100644 oldtests/Blockquotes/Indents.markdown
 delete mode 100644 oldtests/Blockquotes/Nesting.html
 delete mode 100644 oldtests/Blockquotes/Nesting.markdown
 delete mode 100644 oldtests/Blockquotes/Separation.html
 delete mode 100644 oldtests/Blockquotes/Separation.markdown
 delete mode 100644 oldtests/Code/BlankLines.html
 delete mode 100644 oldtests/Code/BlankLines.markdown
 delete mode 100644 oldtests/Code/BlankLinesAtEnd.html
 delete mode 100644 oldtests/Code/BlankLinesAtEnd.markdown
 delete mode 100644 oldtests/Code/FenceMatching.html
 delete mode 100644 oldtests/Code/FenceMatching.markdown
 delete mode 100644 oldtests/Code/FencedCodeBlocks.html
 delete mode 100644 oldtests/Code/FencedCodeBlocks.markdown
 delete mode 100644 oldtests/Code/IndentedCodeBlocks.html
 delete mode 100644 oldtests/Code/IndentedCodeBlocks.markdown
 delete mode 100644 oldtests/Code/IndentedFences.html
 delete mode 100644 oldtests/Code/IndentedFences.markdown
 delete mode 100644 oldtests/Code/IndentedInLists.html
 delete mode 100644 oldtests/Code/IndentedInLists.markdown
 delete mode 100644 oldtests/Code/Inline.html
 delete mode 100644 oldtests/Code/Inline.markdown
 delete mode 100644 oldtests/Code/ListBreakAfter.html
 delete mode 100644 oldtests/Code/ListBreakAfter.markdown
 delete mode 100644 oldtests/Code/WhiteLines.html
 delete mode 100644 oldtests/Code/WhiteLines.markdown
 delete mode 100644 oldtests/Emphasis/Escapes.html
 delete mode 100644 oldtests/Emphasis/Escapes.markdown
 delete mode 100644 oldtests/Emphasis/NestedEmphAndStrong.html
 delete mode 100644 oldtests/Emphasis/NestedEmphAndStrong.markdown
 delete mode 100644 oldtests/Emphasis/Pathological.html
 delete mode 100644 oldtests/Emphasis/Pathological.markdown
 delete mode 100644 oldtests/Emphasis/Punctuation.html
 delete mode 100644 oldtests/Emphasis/Punctuation.markdown
 delete mode 100644 oldtests/HTML/Blocks.html
 delete mode 100644 oldtests/HTML/Blocks.markdown
 delete mode 100644 oldtests/HTML/Inline.html
 delete mode 100644 oldtests/HTML/Inline.markdown
 delete mode 100644 oldtests/HTML/UppercaseTags.html
 delete mode 100644 oldtests/HTML/UppercaseTags.markdown
 delete mode 100644 oldtests/Headers/ATX.html
 delete mode 100644 oldtests/Headers/ATX.markdown
 delete mode 100644 oldtests/Headers/Setext.html
 delete mode 100644 oldtests/Headers/Setext.markdown
 delete mode 100644 oldtests/Links/AngleBrackets.html
 delete mode 100644 oldtests/Links/AngleBrackets.markdown
 delete mode 100644 oldtests/Links/AutoLinks.html
 delete mode 100644 oldtests/Links/AutoLinks.markdown
 delete mode 100644 oldtests/Links/BackticksInLinks.html
 delete mode 100644 oldtests/Links/BackticksInLinks.markdown
 delete mode 100644 oldtests/Links/CaseInsensitiveReferences.html
 delete mode 100644 oldtests/Links/CaseInsensitiveReferences.markdown
 delete mode 100644 oldtests/Links/Entities.html
 delete mode 100644 oldtests/Links/Entities.markdown
 delete mode 100644 oldtests/Links/InlineLinks.html
 delete mode 100644 oldtests/Links/InlineLinks.markdown
 delete mode 100644 oldtests/Links/ParensInURLs.html
 delete mode 100644 oldtests/Links/ParensInURLs.markdown
 delete mode 100644 oldtests/Links/ReferenceLinks.html
 delete mode 100644 oldtests/Links/ReferenceLinks.markdown
 delete mode 100644 oldtests/Lists/CodeBlocksInLists.html
 delete mode 100644 oldtests/Lists/CodeBlocksInLists.markdown
 delete mode 100644 oldtests/Lists/ConsecutiveLists.html
 delete mode 100644 oldtests/Lists/ConsecutiveLists.markdown
 delete mode 100644 oldtests/Lists/EmptyListItem.html
 delete mode 100644 oldtests/Lists/EmptyListItem.markdown
 delete mode 100644 oldtests/Lists/InBlockquote.html
 delete mode 100644 oldtests/Lists/InBlockquote.markdown
 delete mode 100644 oldtests/Lists/Indents.html
 delete mode 100644 oldtests/Lists/Indents.markdown
 delete mode 100644 oldtests/Lists/ListsAndHRs.html
 delete mode 100644 oldtests/Lists/ListsAndHRs.markdown
 delete mode 100644 oldtests/Lists/ListsAndSetextHeaders.html
 delete mode 100644 oldtests/Lists/ListsAndSetextHeaders.markdown
 delete mode 100644 oldtests/Lists/MultipleBlankLines.html
 delete mode 100644 oldtests/Lists/MultipleBlankLines.markdown
 delete mode 100644 oldtests/Lists/Start.html
 delete mode 100644 oldtests/Lists/Start.markdown
 delete mode 100644 oldtests/Lists/Sublists.html
 delete mode 100644 oldtests/Lists/Sublists.markdown
 delete mode 100644 oldtests/Lists/TightAndLoose.html
 delete mode 100644 oldtests/Lists/TightAndLoose.markdown
 delete mode 100644 oldtests/Lists/TightLooseBlockquote.html
 delete mode 100644 oldtests/Lists/TightLooseBlockquote.markdown
 delete mode 100644 oldtests/Lists/TightLooseMore.html
 delete mode 100644 oldtests/Lists/TightLooseMore.markdown
 delete mode 100644 oldtests/Lists/TwoBlankLinesEndList.html
 delete mode 100644 oldtests/Lists/TwoBlankLinesEndList.markdown
 delete mode 100644 oldtests/Makefile
 delete mode 100644 oldtests/Misc/BackslashEscapes.html
 delete mode 100644 oldtests/Misc/BackslashEscapes.markdown
 delete mode 100644 oldtests/Misc/Laziness.html
 delete mode 100644 oldtests/Misc/Laziness.markdown
 delete mode 100644 oldtests/Misc/LineBreaks.html
 delete mode 100644 oldtests/Misc/LineBreaks.markdown
 delete mode 100644 oldtests/Misc/Transitions.html
 delete mode 100644 oldtests/Misc/Transitions.markdown
 delete mode 100644 oldtests/Original/Amps_and_angle_encoding.html
 delete mode 100644 oldtests/Original/Amps_and_angle_encoding.markdown
 delete mode 100644 oldtests/Original/Auto_links.html
 delete mode 100644 oldtests/Original/Auto_links.markdown
 delete mode 100644 oldtests/Original/Backslash_escapes.html
 delete mode 100644 oldtests/Original/Backslash_escapes.markdown
 delete mode 100644 oldtests/Original/Blockquotes_with_code_blocks.html
 delete mode 100644 oldtests/Original/Blockquotes_with_code_blocks.markdown
 delete mode 100644 oldtests/Original/Code_Blocks.html
 delete mode 100644 oldtests/Original/Code_Blocks.markdown
 delete mode 100644 oldtests/Original/Code_Spans.html
 delete mode 100644 oldtests/Original/Code_Spans.markdown
 delete mode 100644 oldtests/Original/Horizontal_rules.html
 delete mode 100644 oldtests/Original/Horizontal_rules.markdown
 delete mode 100644 oldtests/Original/Images.html
 delete mode 100644 oldtests/Original/Images.markdown
 delete mode 100644 oldtests/Original/Inline_HTML_Advanced.html
 delete mode 100644 oldtests/Original/Inline_HTML_Advanced.markdown
 delete mode 100644 oldtests/Original/Inline_HTML_Simple.html
 delete mode 100644 oldtests/Original/Inline_HTML_Simple.markdown
 delete mode 100644 oldtests/Original/Inline_HTML_comments.html
 delete mode 100644 oldtests/Original/Inline_HTML_comments.markdown
 delete mode 100644 oldtests/Original/Links_inline_style.html
 delete mode 100644 oldtests/Original/Links_inline_style.markdown
 delete mode 100644 oldtests/Original/Links_reference_style.html
 delete mode 100644 oldtests/Original/Links_reference_style.markdown
 delete mode 100644 oldtests/Original/Links_shortcut_references.html
 delete mode 100644 oldtests/Original/Links_shortcut_references.markdown
 delete mode 100644 oldtests/Original/Literal_quotes_in_titles.html
 delete mode 100644 oldtests/Original/Literal_quotes_in_titles.markdown
 delete mode 100644 oldtests/Original/Markdown_Documentation_Basics.html
 delete mode 100644 oldtests/Original/Markdown_Documentation_Basics.markdown
 delete mode 100644 oldtests/Original/Markdown_Documentation_Syntax.html
 delete mode 100644 oldtests/Original/Markdown_Documentation_Syntax.markdown
 delete mode 100644 oldtests/Original/Nested_blockquotes.html
 delete mode 100644 oldtests/Original/Nested_blockquotes.markdown
 delete mode 100644 oldtests/Original/Ordered_and_unordered_lists.html
 delete mode 100644 oldtests/Original/Ordered_and_unordered_lists.markdown
 delete mode 100644 oldtests/Original/README
 delete mode 100644 oldtests/Original/Strong_and_em_together.html
 delete mode 100644 oldtests/Original/Strong_and_em_together.markdown
 delete mode 100644 oldtests/Original/Tabs.html
 delete mode 100644 oldtests/Original/Tabs.markdown
 delete mode 100644 oldtests/Original/Tidyness.html
 delete mode 100644 oldtests/Original/Tidyness.markdown
 delete mode 100644 oldtests/Tabs/TabConversionUnicode.html
 delete mode 100644 oldtests/Tabs/TabConversionUnicode.markdown

(limited to 'Makefile')

diff --git a/Makefile b/Makefile
index 671d30d..8d35b9d 100644
--- a/Makefile
+++ b/Makefile
@@ -5,7 +5,7 @@ DATADIR?=data
 
 PROG?=./stmd
 
-.PHONY: all oldtests test spec benchjs testjs
+.PHONY: all test spec benchjs testjs
 all: $(SRCDIR)/case_fold_switch.inc $(PROG)
 
 README.html: README.md template.html
@@ -28,9 +28,6 @@ spec.pdf: spec.md template.tex specfilter.hs
 	   --number-sections -V documentclass=report -V tocdepth=2 \
 	   -V classoption=twosides
 
-oldtests:
-	make -C oldtests --quiet clean all
-
 test: spec.txt
 	perl runtests.pl $< $(PROG)
 
@@ -63,7 +60,8 @@ dingus:
 	cd js && echo "Starting dingus server at http://localhost:9000" && python -m SimpleHTTPServer 9000
 
 leakcheck: $(PROG)
-	cat oldtests/*/*.markdown | valgrind --leak-check=full --dsymutil=yes $(PROG)
+	# TODO produce leaktest.md that tests everything
+	cat leaktest.md | valgrind --leak-check=full --dsymutil=yes $(PROG)
 
 operf: $(PROG)
 	operf $(PROG) /dev/null
diff --git a/oldtests/Blockquotes/Indents.html b/oldtests/Blockquotes/Indents.html
deleted file mode 100644
index fd98ee8..0000000
--- a/oldtests/Blockquotes/Indents.html
+++ /dev/null
@@ -1,12 +0,0 @@
-
    
-
    one
-blockquote
    
-
    
-
    
-
    
-
    
-
    triply nested
-triply nested
    
-
    
-
    
-
    
diff --git a/oldtests/Blockquotes/Indents.markdown b/oldtests/Blockquotes/Indents.markdown
deleted file mode 100644
index f9342ff..0000000
--- a/oldtests/Blockquotes/Indents.markdown
+++ /dev/null
@@ -1,5 +0,0 @@
-> one
- > blockquote
-
->>> triply nested
-   >   >   > triply nested
diff --git a/oldtests/Blockquotes/Nesting.html b/oldtests/Blockquotes/Nesting.html
deleted file mode 100644
index f40e999..0000000
--- a/oldtests/Blockquotes/Nesting.html
+++ /dev/null
@@ -1,32 +0,0 @@
-
    These are all equivalent:
    
-
    
-
    
-
    nested
-blockquote
    
-
    
-
    
-
    
-
    
-
    nested
-blockquote
    
-
    
-
    
-
    
-
    
-
    nested
-blockquote
    
-
    
-
    
-
    
-
    
-
    nested
-blockquote
    
-
    
-
    
-
    This is not:
    
-
    
-
    nested
    
-
    
-
    blockquote
    
-
    
-
    
diff --git a/oldtests/Blockquotes/Nesting.markdown b/oldtests/Blockquotes/Nesting.markdown
deleted file mode 100644
index 3d67843..0000000
--- a/oldtests/Blockquotes/Nesting.markdown
+++ /dev/null
@@ -1,22 +0,0 @@
-These are all equivalent:
-
-> > nested
-> > blockquote
-
-
->> nested
->> blockquote
-
-
-> > nested
-blockquote
-
-
-> > nested
-> blockquote
-
-
-This is not:
-
-> nested
-> > blockquote
diff --git a/oldtests/Blockquotes/Separation.html b/oldtests/Blockquotes/Separation.html
deleted file mode 100644
index 910d545..0000000
--- a/oldtests/Blockquotes/Separation.html
+++ /dev/null
@@ -1,39 +0,0 @@
-
    One blockquote, two paragraphs:
    
-
    
-
    one
    
-
    two
    
-
    
-
    Two blockquotes:
    
-
    
-
    one
    
-
    
-
    
-
    two
    
-
    
-
    Nested blockquote, two paragraphs:
    
-
    
-
    
-
    one
    
-
    two
    
-
    
-
    
-
    Nested blockquote, two blockquotes:
    
-
    
-
    
-
    one
    
-
    
-
    
-
    two
    
-
    
-
    
-
    Two nested blockquotes:
    
-
    
-
    
-
    one
    
-
    
-
    
-
    
-
    
-
    two
    
-
    
-
    
diff --git a/oldtests/Blockquotes/Separation.markdown b/oldtests/Blockquotes/Separation.markdown
deleted file mode 100644
index 823d865..0000000
--- a/oldtests/Blockquotes/Separation.markdown
+++ /dev/null
@@ -1,29 +0,0 @@
-One blockquote, two paragraphs:
-
-> one
->
-> two
-
-Two blockquotes:
-
-> one
-
-> two
-
-Nested blockquote, two paragraphs:
-
-> > one
-> >
-> > two
-
-Nested blockquote, two blockquotes:
-
-> > one
->
-> > two
-
-Two nested blockquotes:
-
-> > one
-
-> > two
diff --git a/oldtests/Code/BlankLines.html b/oldtests/Code/BlankLines.html
deleted file mode 100644
index ae0abf7..0000000
--- a/oldtests/Code/BlankLines.html
+++ /dev/null
@@ -1,33 +0,0 @@
-
    foo
-
-
-
-bar
-
    
-
    
-
    foo
-
-
-
-bar
-
    
-
    
-
    foo
-
-    
-
-bar
-
    
-
      
-
    1. One
      
-
      CodeA
-
-CodeB
-
      2. 
-
    2. Two
      
-
      CodeA
-
      3. 
-
    
-
      
-
    1. One
      2. 
-
    
diff --git a/oldtests/Code/BlankLines.markdown b/oldtests/Code/BlankLines.markdown
deleted file mode 100644
index b0d5a0c..0000000
--- a/oldtests/Code/BlankLines.markdown
+++ /dev/null
@@ -1,28 +0,0 @@
-    foo
-
-
-
-    bar
->     foo
->
->
->
->     bar
-    foo
-
-        
- 
-    bar
-
-1. One
-
-       CodeA
-
-       CodeB
-
-2. Two
-
-       CodeA
-
-
-1. One
diff --git a/oldtests/Code/BlankLinesAtEnd.html b/oldtests/Code/BlankLinesAtEnd.html
deleted file mode 100644
index ac803d9..0000000
--- a/oldtests/Code/BlankLinesAtEnd.html
+++ /dev/null
@@ -1,14 +0,0 @@
-
      
-
    • List
      
-
      code
-
      • 
-
    
-
      
-
    • one
      • 
-
    • two
      • 
-
    
-
      
-
    • one
-not code
      • 
-
    • two
      • 
-
    
diff --git a/oldtests/Code/BlankLinesAtEnd.markdown b/oldtests/Code/BlankLinesAtEnd.markdown
deleted file mode 100644
index 55879ae..0000000
--- a/oldtests/Code/BlankLinesAtEnd.markdown
+++ /dev/null
@@ -1,14 +0,0 @@
-* List
-
-      code
-
-
-  * one
-  * two
-
-
-
-* one
-      not code
-
-* two
diff --git a/oldtests/Code/FenceMatching.html b/oldtests/Code/FenceMatching.html
deleted file mode 100644
index 4c7468e..0000000
--- a/oldtests/Code/FenceMatching.html
+++ /dev/null
@@ -1,8 +0,0 @@
-
    ```
-
    
-
    
-`````
-
-````
-
-
    
diff --git a/oldtests/Code/FenceMatching.markdown b/oldtests/Code/FenceMatching.markdown
deleted file mode 100644
index d86169a..0000000
--- a/oldtests/Code/FenceMatching.markdown
+++ /dev/null
@@ -1,10 +0,0 @@
-````abc
-```
-````
-``````blah
-
-`````
-
-````
-
-```````````
diff --git a/oldtests/Code/FencedCodeBlocks.html b/oldtests/Code/FencedCodeBlocks.html
deleted file mode 100644
index 4813d72..0000000
--- a/oldtests/Code/FencedCodeBlocks.html
+++ /dev/null
@@ -1,24 +0,0 @@
-
    This is a fenced code block:
    
-
    pairs :: [(Int,Char)]
-pairs = [(x,y) | x <- [0..10], y <- ['a'..'z']]
-
    
-
    Here is one with tildes:
    
-
    pairs :: [(Int,Char)]
-pairs = [(x,y) | x <- [0..10], y <- ['a'..'z']]
-
    
-
    More metadata:
    
-
    pairs :: [(Int,Char)]
-pairs = [(x,y) | x <- [0..10], y <- ['a'..'z']]
-
    
-
    More backticks:
    
-
    pairs :: [(Int,Char)]
-pairs = [(x,y) | x <- [0..10], y <- ['a'..'z']]
-
-backticks :: String
-backticks = "`````"
-
    
-
    Without an end:
    
-
    code with
-no end
-
-
    
diff --git a/oldtests/Code/FencedCodeBlocks.markdown b/oldtests/Code/FencedCodeBlocks.markdown
deleted file mode 100644
index 6ccc6be..0000000
--- a/oldtests/Code/FencedCodeBlocks.markdown
+++ /dev/null
@@ -1,35 +0,0 @@
-This is a fenced code block:
-```haskell
-pairs :: [(Int,Char)]
-pairs = [(x,y) | x <- [0..10], y <- ['a'..'z']]
-```
-Here is one with tildes:
-
-~~~ haskell
-pairs :: [(Int,Char)]
-pairs = [(x,y) | x <- [0..10], y <- ['a'..'z']]
-~~~
-
-More metadata:
-
-```haskell numberLines start=50
-pairs :: [(Int,Char)]
-pairs = [(x,y) | x <- [0..10], y <- ['a'..'z']]
-```
-
-More backticks:
-
-```````` haskell
-pairs :: [(Int,Char)]
-pairs = [(x,y) | x <- [0..10], y <- ['a'..'z']]
-
-backticks :: String
-backticks = "`````"
-`````````````
-
-Without an end:
-
-```
-code with
-no end
-
diff --git a/oldtests/Code/IndentedCodeBlocks.html b/oldtests/Code/IndentedCodeBlocks.html
deleted file mode 100644
index 0b9b7e7..0000000
--- a/oldtests/Code/IndentedCodeBlocks.html
+++ /dev/null
@@ -1,22 +0,0 @@
-
    Indented code with two space indent in first and last line:
    
-
      two spaces *hello*
-{ more }
-
-  and
-
    
-
    Indented code requires a leading/trailing blank line:
-quick-command --option "$*"
    
-
    Indented code does not require a trailing blank line:
    
-
    code
-
    
-
    and not code.
    
-
    Code in blockquote:
    
-
    
-
    code
-
    
-
    
-
    Code in list:
    
-
      
-
    1. code
-
      2. 
-
    
diff --git a/oldtests/Code/IndentedCodeBlocks.markdown b/oldtests/Code/IndentedCodeBlocks.markdown
deleted file mode 100644
index 2a99db0..0000000
--- a/oldtests/Code/IndentedCodeBlocks.markdown
+++ /dev/null
@@ -1,22 +0,0 @@
-Indented code with two space indent in first and last line:
-
-      two spaces *hello*
-    { more }
-
-      and
-
-Indented code requires a leading/trailing blank line:
-    quick-command --option "$*"
-
-Indented code does not require a trailing blank line:
-
-    code
-and not code.
-
-Code in blockquote:
-
->     code
-
-Code in list:
-
-1.     code
diff --git a/oldtests/Code/IndentedFences.html b/oldtests/Code/IndentedFences.html
deleted file mode 100644
index 66e76da..0000000
--- a/oldtests/Code/IndentedFences.html
+++ /dev/null
@@ -1,20 +0,0 @@
-
    a
-
    
-
    z
-
    
-
    a
-a
-a
- a
-
    
-
      
-
    • foo
      
-
           Hello
-
-World
-
      • 
-
    
-
    
-
    a
-
    
-
    
diff --git a/oldtests/Code/IndentedFences.markdown b/oldtests/Code/IndentedFences.markdown
deleted file mode 100644
index 098545f..0000000
--- a/oldtests/Code/IndentedFences.markdown
+++ /dev/null
@@ -1,26 +0,0 @@
-  ```
-  a
-  ```
-
-  ```
-z
-```
-
-  ```
-a
- a
-  a
-   a
-  ```
-
-* foo
-
-     ```
-          Hello
-    
-  World
-     ```
-
->  ```
->a
->```
diff --git a/oldtests/Code/IndentedInLists.html b/oldtests/Code/IndentedInLists.html
deleted file mode 100644
index 76ed424..0000000
--- a/oldtests/Code/IndentedInLists.html
+++ /dev/null
@@ -1,22 +0,0 @@
-
      
-
    • code starts here
-
      • 
-
    
-
      
-
    1. foo
      
-
      code starts here
-
      2. 
-
    2. foo
      
-
      code starts here
-
      3. 
-
    
-
      
-
    • foo
      
-
      code starts here
-
      
-
        
-
      • foo
        
-
        code starts here
-
        • 
-
      • 
-
    
diff --git a/oldtests/Code/IndentedInLists.markdown b/oldtests/Code/IndentedInLists.markdown
deleted file mode 100644
index 54e1af1..0000000
--- a/oldtests/Code/IndentedInLists.markdown
+++ /dev/null
@@ -1,17 +0,0 @@
--     code starts here
-
-1.  foo
-
-        code starts here
-
-2. foo
-
-       code starts here
-
-- foo
-
-      code starts here
-
-  - foo
-
-        code starts here
diff --git a/oldtests/Code/Inline.html b/oldtests/Code/Inline.html
deleted file mode 100644
index 9c52790..0000000
--- a/oldtests/Code/Inline.html
+++ /dev/null
@@ -1,13 +0,0 @@
-
    All of these are equivalent:
    
-
      
-
    • *hi*
      • 
-
    • *hi*
      • 
-
    • *hi*
      • 
-
    • *hi*
      • 
-
    • *hi*
      • 
-
    
-
    Backticks in code spans:
    
-
      
-
    • ``code``
      • 
-
    • ``code``
      • 
-
    
diff --git a/oldtests/Code/Inline.markdown b/oldtests/Code/Inline.markdown
deleted file mode 100644
index 38e5b0c..0000000
--- a/oldtests/Code/Inline.markdown
+++ /dev/null
@@ -1,13 +0,0 @@
-All of these are equivalent:
-
-- `*hi*`
-- ` *hi* `
-- ``*hi* ``
-- ````*hi*````
-- `*hi*
-  `
-
-Backticks in code spans:
-
-- ``` ``code`` ```
-- ` ``code`` `
diff --git a/oldtests/Code/ListBreakAfter.html b/oldtests/Code/ListBreakAfter.html
deleted file mode 100644
index 29d6d5e..0000000
--- a/oldtests/Code/ListBreakAfter.html
+++ /dev/null
@@ -1,30 +0,0 @@
-
      
-
    • foo
      
-
        
-
      • bar
        
-
        code1
-code2
-
        
-
        code?
        • 
-
      • 
-
    • foo
      
-
        
-
      • bar
        
-
        code1
-code2
-
        • 
-
      • 
-
    
-
    code?
-
    
-
      
-
    • foo
-
        
-
      • bar
        
-
        code1
-code2
-
        • 
-
      • 
-
    
-
    code?
-
    
diff --git a/oldtests/Code/ListBreakAfter.markdown b/oldtests/Code/ListBreakAfter.markdown
deleted file mode 100644
index 4fa79f1..0000000
--- a/oldtests/Code/ListBreakAfter.markdown
+++ /dev/null
@@ -1,26 +0,0 @@
-* foo
-  * bar
-
-        code1
-        code2
-
-    code?
-
-* foo
-  * bar
-
-        code1
-        code2
-
-
-    code?
-
-* foo
-  * bar
-
-        code1
-        code2
-
-
-
-    code?
diff --git a/oldtests/Code/WhiteLines.html b/oldtests/Code/WhiteLines.html
deleted file mode 100644
index 7fa137f..0000000
--- a/oldtests/Code/WhiteLines.html
+++ /dev/null
@@ -1,7 +0,0 @@
-
    ABC
-  
- 
-
-DEF
-
    
-
    GHI
    
diff --git a/oldtests/Code/WhiteLines.markdown b/oldtests/Code/WhiteLines.markdown
deleted file mode 100644
index ea17af7..0000000
--- a/oldtests/Code/WhiteLines.markdown
+++ /dev/null
@@ -1,9 +0,0 @@
-    ABC
-      
-     
-  
-    DEF
-           
-     
-
-GHI
diff --git a/oldtests/Emphasis/Escapes.html b/oldtests/Emphasis/Escapes.html
deleted file mode 100644
index 17c9e2d..0000000
--- a/oldtests/Emphasis/Escapes.html
+++ /dev/null
@@ -1 +0,0 @@
-
    hi* there
    
diff --git a/oldtests/Emphasis/Escapes.markdown b/oldtests/Emphasis/Escapes.markdown
deleted file mode 100644
index 4f14698..0000000
--- a/oldtests/Emphasis/Escapes.markdown
+++ /dev/null
@@ -1 +0,0 @@
-*hi\* there*
\ No newline at end of file
diff --git a/oldtests/Emphasis/NestedEmphAndStrong.html b/oldtests/Emphasis/NestedEmphAndStrong.html
deleted file mode 100644
index b41b527..0000000
--- a/oldtests/Emphasis/NestedEmphAndStrong.html
+++ /dev/null
@@ -1,66 +0,0 @@
-
      
-
    1. test test
      2. 
-
    2. test test
      3. 
-
    3. test test
      4. 
-
    4. test test
      5. 
-
    5. test test
      6. 
-
    6. test test
      7. 
-
    7. test test
      8. 
-
    8. test test
      9. 
-
    9. test test
      10. 
-
    10. test test
      11. 
-
    11. test test
      12. 
-
    12. test test
      13. 
-
    13. test test
      14. 
-
    14. test test
      15. 
-
    15. test test
      16. 
-
    16. test test
      17. 
-
    
-
    Incorrect nesting:
    
-
      
-
    1. *test test* test
      2. 
-
    2. _test test_ test
      3. 
-
    3. **test test* test*
      4. 
-
    4. __test␣test_␣test_
      5. 
-
    5. test  test test
      6. 
-
    6. test  test test
      7. 
-
    7. test test test
      8. 
-
    8. test test test
      9. 
-
    
-
    No emphasis:
    
-
      
-
    1. test* test *test
      2. 
-
    2. test** test **test
      3. 
-
    3. test_ test _test
      4. 
-
    4. test__ test __test
      5. 
-
    
-
    Middle-word emphasis (asterisks):
    
-
      
-
    1. ab
      2. 
-
    2. ab
      3. 
-
    3. abc
      4. 
-
    4. ab
      5. 
-
    5. ab
      6. 
-
    6. abc
      7. 
-
    
-
    Middle-word emphasis (underscore):
    
-
      
-
    1. _a_b
      2. 
-
    2. a_b_
      3. 
-
    3. a_b_c
      4. 
-
    4. __a__b
      5. 
-
    5. a__b__
      6. 
-
    6. a__b__c
      7. 
-
    7. my_precious_file.txt
      8. 
-
    
-
    Tricky Cases:
    
-
      
-
    1. E**. Test TestTestTest
      2. 
-
    2. E**. Test Test Test Test
      3. 
-
    
-
    Overlong emphasis:
    
-
    Name: ____________
    
-Organization: ____
    
-Region/Country: __
    
-
    _____Cut here_____
    
-
    ____Cut here____
    
diff --git a/oldtests/Emphasis/NestedEmphAndStrong.markdown b/oldtests/Emphasis/NestedEmphAndStrong.markdown
deleted file mode 100644
index ec7da25..0000000
--- a/oldtests/Emphasis/NestedEmphAndStrong.markdown
+++ /dev/null
@@ -1,69 +0,0 @@
-1.  ***test test***
-2.  ___test test___
-3.  *test **test***
-4.  **test *test***
-5.  ***test* test**
-6.  ***test** test*
-7.  ***test* test**
-8.  **test *test***
-9.  *test **test***
-10. _test __test___
-11. __test _test___
-12. ___test_ test__
-13. ___test__ test_
-14. ___test_ test__
-15. __test _test___
-16. _test __test___
-
-Incorrect nesting:
-
-1. *test **test* test**
-2. _test __test_ test__
-3. **test *test** test*
-4. __test _test__ test_
-5. *test  *test* test*
-6. _test  _test_ test_
-7. **test **test** test**
-8. __test __test__ test__
-
-No emphasis:
-
-1. test* test *test
-2. test** test **test
-3. test_ test _test
-4. test__ test __test
-
-Middle-word emphasis (asterisks):
-
-1.  *a*b
-2.   a*b*
-3.   a*b*c
-4. **a**b
-5.   a**b**
-6.   a**b**c
-
-Middle-word emphasis (underscore):
-
-1.  _a_b
-2.   a_b_
-3.   a_b_c
-4. __a__b
-5.   a__b__
-6.   a__b__c
-7.   my_precious_file.txt
-
-Tricky Cases:
-
-1.  E**. **Test** TestTestTest
-2.  E**. **Test** Test Test Test
-
-Overlong emphasis:
-
-Name: ____________  
-Organization: ____  
-Region/Country: __
-
-_____Cut here_____
-
-____Cut here____
-
diff --git a/oldtests/Emphasis/Pathological.html b/oldtests/Emphasis/Pathological.html
deleted file mode 100644
index 37eb9fa..0000000
--- a/oldtests/Emphasis/Pathological.html
+++ /dev/null
@@ -1,24 +0,0 @@
-
    This input can take a long time to parse in some implementations.
    
-
    *a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-aaaaa
    
-
    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa**
    
diff --git a/oldtests/Emphasis/Pathological.markdown b/oldtests/Emphasis/Pathological.markdown
deleted file mode 100644
index 5deb95e..0000000
--- a/oldtests/Emphasis/Pathological.markdown
+++ /dev/null
@@ -1,26 +0,0 @@
-This input can take a long time to parse in some implementations.
-
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-*a
-aaaaa
-
-*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**
diff --git a/oldtests/Emphasis/Punctuation.html b/oldtests/Emphasis/Punctuation.html
deleted file mode 100644
index 6061b81..0000000
--- a/oldtests/Emphasis/Punctuation.html
+++ /dev/null
@@ -1,10 +0,0 @@
-
    Here is a _ that is cool.
    
-
    Foo.
    
-
    Foo.
    
-
    Foo.
    
-
    Foo.
    
-
    Foo.
    
-
    Foo.
    
-
    Foo. Foo? Foo! Foo: Foo; (Foo)
    
-
    Foo. Foo? Foo! Foo: Foo; (Foo)
    
-
    Foo. Foo? Foo! Foo: Foo; (Foo)
    
diff --git a/oldtests/Emphasis/Punctuation.markdown b/oldtests/Emphasis/Punctuation.markdown
deleted file mode 100644
index e3f23b8..0000000
--- a/oldtests/Emphasis/Punctuation.markdown
+++ /dev/null
@@ -1,19 +0,0 @@
-Here is a _ that is _cool_.
-
-_Foo._
-
-__Foo.__
-
-___Foo.___
-
-_Foo_.
-
-__Foo__.
-
-___Foo___.
-
-_Foo_. _Foo_? _Foo_! _Foo_: _Foo_; (_Foo_)
-
-__Foo__. __Foo__? __Foo__! __Foo__: __Foo__; (__Foo__)
-
-___Foo___. ___Foo___? ___Foo___! ___Foo___: ___Foo___; (___Foo___)
diff --git a/oldtests/HTML/Blocks.html b/oldtests/HTML/Blocks.html
deleted file mode 100644
index dc80335..0000000
--- a/oldtests/HTML/Blocks.html
+++ /dev/null
@@ -1,18 +0,0 @@
-
    
-  
    
-   *raw html*
-  
    
-
    
-
    
-
    
-
    this is markdown
    
-
    
-
    
-
-
-
    
-* raw html with trailing space 
-
    
diff --git a/oldtests/HTML/Blocks.markdown b/oldtests/HTML/Blocks.markdown
deleted file mode 100644
index a83fa66..0000000
--- a/oldtests/HTML/Blocks.markdown
+++ /dev/null
@@ -1,26 +0,0 @@
-
    
-  
    
-   *raw html*
-  
    
-
    
-
-
    
-
    
-
-*this is markdown*
-
-
    
-
    
-
-
-
-
-
-
    
-* raw html with trailing space 
-
    
diff --git a/oldtests/HTML/Inline.html b/oldtests/HTML/Inline.html
deleted file mode 100644
index 94d40ac..0000000
--- a/oldtests/HTML/Inline.html
+++ /dev/null
@@ -1,8 +0,0 @@
-
    hi
-hi
-
-Hello  there.
-A line
    break.
-
    
diff --git a/oldtests/HTML/Inline.markdown b/oldtests/HTML/Inline.markdown
deleted file mode 100644
index 2259421..0000000
--- a/oldtests/HTML/Inline.markdown
+++ /dev/null
@@ -1,8 +0,0 @@
-hi
-`hi`
-
-Hello  there.
-A line
    break.
-
diff --git a/oldtests/HTML/UppercaseTags.html b/oldtests/HTML/UppercaseTags.html
deleted file mode 100644
index 8d2d828..0000000
--- a/oldtests/HTML/UppercaseTags.html
+++ /dev/null
@@ -1,4 +0,0 @@
-
    
-this is a block
-
    
-
    Here is some inline html.
    
diff --git a/oldtests/HTML/UppercaseTags.markdown b/oldtests/HTML/UppercaseTags.markdown
deleted file mode 100644
index b476ffb..0000000
--- a/oldtests/HTML/UppercaseTags.markdown
+++ /dev/null
@@ -1,5 +0,0 @@
-
    
-this is a block
-
    
-
-Here is some inline html.
\ No newline at end of file
diff --git a/oldtests/Headers/ATX.html b/oldtests/Headers/ATX.html
deleted file mode 100644
index f375b98..0000000
--- a/oldtests/Headers/ATX.html
+++ /dev/null
@@ -1,14 +0,0 @@
-
    One
    
-
    Two
    
-
    Three
    
-
    Four
    
-
    Five
    
-
    Six
    
-
    ####### Seven
    
-
    Three with
    
-
    Spacing    doesn't    matter
    
-
    Escaped final #
    
-
    ## Not a header
    
-
    #5 not a header
    
-
    
-
    (empty header)
    
diff --git a/oldtests/Headers/ATX.markdown b/oldtests/Headers/ATX.markdown
deleted file mode 100644
index f687aa5..0000000
--- a/oldtests/Headers/ATX.markdown
+++ /dev/null
@@ -1,20 +0,0 @@
-# One
-## Two
-### Three
-#### Four
-##### Five
-
-###### Six
-
-####### Seven
-
-### Three with ###
-##      Spacing    doesn't    matter    ##      
-## Escaped final \##
-
-\## Not a header
-
-#5 not a header
-
-##
-(empty header)
diff --git a/oldtests/Headers/Setext.html b/oldtests/Headers/Setext.html
deleted file mode 100644
index 787fb02..0000000
--- a/oldtests/Headers/Setext.html
+++ /dev/null
@@ -1,9 +0,0 @@
-
    Level one
    
-
    Two
    
-
    In a paragraph
    
-
    Level two
    
-
    more text
    
-
    ======
-no empty headers
    
-
    not a header
    
-
    
diff --git a/oldtests/Headers/Setext.markdown b/oldtests/Headers/Setext.markdown
deleted file mode 100644
index da0c7e2..0000000
--- a/oldtests/Headers/Setext.markdown
+++ /dev/null
@@ -1,17 +0,0 @@
-Level one
-=========
-
-Two
----
-
-In a paragraph
-
-Level two
----------
-more text
-
-======
-no empty headers
-
-not a header
------------- -----
diff --git a/oldtests/Links/AngleBrackets.html b/oldtests/Links/AngleBrackets.html
deleted file mode 100644
index 21ac00d..0000000
--- a/oldtests/Links/AngleBrackets.html
+++ /dev/null
@@ -1,3 +0,0 @@
-
    silly URL with angle brackets.
    
-
    link.
    
-
    link.
    
diff --git a/oldtests/Links/AngleBrackets.markdown b/oldtests/Links/AngleBrackets.markdown
deleted file mode 100644
index c2e06ff..0000000
--- a/oldtests/Links/AngleBrackets.markdown
+++ /dev/null
@@ -1,7 +0,0 @@
-[silly URL with angle brackets]().
-
-[link]( "title").
-
-[link][].
-
-[link]:  "title"
diff --git a/oldtests/Links/AutoLinks.html b/oldtests/Links/AutoLinks.html
deleted file mode 100644
index 092353f..0000000
--- a/oldtests/Links/AutoLinks.html
+++ /dev/null
@@ -1,7 +0,0 @@
-
    http://google.com?query=blah&time=15
-someone.else@somedomain.com
-ftp://old.ftp.server.edu
-git://some.git.repo/project.git
-
-<http://not.an autolink>
-<relative/not/autolink>
    
diff --git a/oldtests/Links/AutoLinks.markdown b/oldtests/Links/AutoLinks.markdown
deleted file mode 100644
index bf95b8d..0000000
--- a/oldtests/Links/AutoLinks.markdown
+++ /dev/null
@@ -1,7 +0,0 @@
-
-
-
-
-
-
-
diff --git a/oldtests/Links/BackticksInLinks.html b/oldtests/Links/BackticksInLinks.html
deleted file mode 100644
index ff70383..0000000
--- a/oldtests/Links/BackticksInLinks.html
+++ /dev/null
@@ -1 +0,0 @@
-
    the right bracket character (])
    
diff --git a/oldtests/Links/BackticksInLinks.markdown b/oldtests/Links/BackticksInLinks.markdown
deleted file mode 100644
index 539fd52..0000000
--- a/oldtests/Links/BackticksInLinks.markdown
+++ /dev/null
@@ -1 +0,0 @@
-[the right bracket character (`]`)](/url)
diff --git a/oldtests/Links/CaseInsensitiveReferences.html b/oldtests/Links/CaseInsensitiveReferences.html
deleted file mode 100644
index afe4557..0000000
--- a/oldtests/Links/CaseInsensitiveReferences.html
+++ /dev/null
@@ -1 +0,0 @@
-
    Толпой is a Russian word.
    
diff --git a/oldtests/Links/CaseInsensitiveReferences.markdown b/oldtests/Links/CaseInsensitiveReferences.markdown
deleted file mode 100644
index f9653b9..0000000
--- a/oldtests/Links/CaseInsensitiveReferences.markdown
+++ /dev/null
@@ -1,3 +0,0 @@
-[Толпой] is a Russian word.
-
-[ТОЛПОЙ]: /url
diff --git a/oldtests/Links/Entities.html b/oldtests/Links/Entities.html
deleted file mode 100644
index 252dadb..0000000
--- a/oldtests/Links/Entities.html
+++ /dev/null
@@ -1,2 +0,0 @@
-
    http://göögle.com
    
-
    hi
    
diff --git a/oldtests/Links/Entities.markdown b/oldtests/Links/Entities.markdown
deleted file mode 100644
index d81ee36..0000000
--- a/oldtests/Links/Entities.markdown
+++ /dev/null
@@ -1,3 +0,0 @@
-
-
-[hi](/url "göögle & yahoo")
diff --git a/oldtests/Links/InlineLinks.html b/oldtests/Links/InlineLinks.html
deleted file mode 100644
index ae33f33..0000000
--- a/oldtests/Links/InlineLinks.html
+++ /dev/null
@@ -1,10 +0,0 @@
-
      
-
    1. link
      2. 
-
    2. link
      3. 
-
    3. link
      4. 
-
    4. link with
-linebreak.
      5. 
-
    5. link
      6. 
-
    6. [not a link] (/url)
      7. 
-
    
diff --git a/oldtests/Links/InlineLinks.markdown b/oldtests/Links/InlineLinks.markdown
deleted file mode 100644
index a822c4d..0000000
--- a/oldtests/Links/InlineLinks.markdown
+++ /dev/null
@@ -1,9 +0,0 @@
-1. [link](/url)
-2. [link](/url "title")
-3. [link](/url
- "title")
-4. [link *with
-linebreak*](     "title
-with linebreak").
-5. [link](/url(withparens) 'and single quoted title')
-6. [not a link] (/url)
diff --git a/oldtests/Links/ParensInURLs.html b/oldtests/Links/ParensInURLs.html
deleted file mode 100644
index 9cd6de7..0000000
--- a/oldtests/Links/ParensInURLs.html
+++ /dev/null
@@ -1,6 +0,0 @@
-
    Inline link 1 with parens.
    
-
    Inline link 2 with parens.
    
-
    Inline link 3 with non-escaped parens.
    
-
    Inline link 4 with non-escaped parens.
    
-
    Reference link 1 with parens.
    
-
    Reference link 2 with parens.
    
diff --git a/oldtests/Links/ParensInURLs.markdown b/oldtests/Links/ParensInURLs.markdown
deleted file mode 100644
index bb7be4f..0000000
--- a/oldtests/Links/ParensInURLs.markdown
+++ /dev/null
@@ -1,14 +0,0 @@
-[Inline link 1 with parens](/url\(test\) "title").
-
-[Inline link 2 with parens]( "title").
-
-[Inline link 3 with non-escaped parens](/url(test) "title").
-
-[Inline link 4 with non-escaped parens]( "title").
-
-[Reference link 1 with parens][1].
-
-[Reference link 2 with parens][2].
-
-  [1]: /url(test) "title"
-  [2]:  "title"
diff --git a/oldtests/Links/ReferenceLinks.html b/oldtests/Links/ReferenceLinks.html
deleted file mode 100644
index 397cdb2..0000000
--- a/oldtests/Links/ReferenceLinks.html
+++ /dev/null
@@ -1,7 +0,0 @@
-
      
-
    1. Link references can be defined anywhere.
      2. 
-
    
-
    
-
    another one
    
-
    
diff --git a/oldtests/Links/ReferenceLinks.markdown b/oldtests/Links/ReferenceLinks.markdown
deleted file mode 100644
index ebcf5a9..0000000
--- a/oldtests/Links/ReferenceLinks.markdown
+++ /dev/null
@@ -1,10 +0,0 @@
-1.  [Link references] can be defined anywhere.
-
-    [Link references]: /url
-      (even in a list item)
-
-> [another] one
->
-> [another]:
-> /foo "can break
-> lines"
diff --git a/oldtests/Lists/CodeBlocksInLists.html b/oldtests/Lists/CodeBlocksInLists.html
deleted file mode 100644
index fcd3e2a..0000000
--- a/oldtests/Lists/CodeBlocksInLists.html
+++ /dev/null
@@ -1,14 +0,0 @@
-
      
-
    1. list item
-code
      2. 
-
    2. list item
      
-
      code
-
      3. 
-
    3. code
-
      4. 
-
    4. code
-
      5. 
-
    5. code
-code
-
      6. 
-
    
diff --git a/oldtests/Lists/CodeBlocksInLists.markdown b/oldtests/Lists/CodeBlocksInLists.markdown
deleted file mode 100644
index 7730808..0000000
--- a/oldtests/Lists/CodeBlocksInLists.markdown
+++ /dev/null
@@ -1,18 +0,0 @@
-1. list item
-       code
-
-2. list item
-   ~~~
-   code
-   ~~~
-
-3. ~~~
-   code
-   ~~~
-
-4. ~~~
-   code
-   ~~~
-
-5.     code
-       code
diff --git a/oldtests/Lists/ConsecutiveLists.html b/oldtests/Lists/ConsecutiveLists.html
deleted file mode 100644
index f8f9098..0000000
--- a/oldtests/Lists/ConsecutiveLists.html
+++ /dev/null
@@ -1,20 +0,0 @@
-
      
-
    • one
      • 
-
    • one
      • 
-
    
-
      
-
    • two
      • 
-
    • two
      • 
-
    
-
      
-
    • three
      • 
-
    • three
      • 
-
    
-
      
-
    1. four
      2. 
-
    2. four
      3. 
-
    
-
      
-
    1. five
      2. 
-
    2. five
      3. 
-
    
diff --git a/oldtests/Lists/ConsecutiveLists.markdown b/oldtests/Lists/ConsecutiveLists.markdown
deleted file mode 100644
index c4faa54..0000000
--- a/oldtests/Lists/ConsecutiveLists.markdown
+++ /dev/null
@@ -1,10 +0,0 @@
-* one
-* one
-+ two
-+ two
-- three
-- three
-1. four
-1. four
-1) five
-1) five
diff --git a/oldtests/Lists/EmptyListItem.html b/oldtests/Lists/EmptyListItem.html
deleted file mode 100644
index 2c23fe1..0000000
--- a/oldtests/Lists/EmptyListItem.html
+++ /dev/null
@@ -1,10 +0,0 @@
-
      
-
    • one
      • 
-
    • 
-
    • three
      • 
-
    
-
      
-
    1. one
      2. 
-
    2. 
-
    3. three
      4. 
-
    
diff --git a/oldtests/Lists/EmptyListItem.markdown b/oldtests/Lists/EmptyListItem.markdown
deleted file mode 100644
index d30cbc3..0000000
--- a/oldtests/Lists/EmptyListItem.markdown
+++ /dev/null
@@ -1,7 +0,0 @@
-- one
-- 
-- three
-
-1. one
-2.
-3. three
diff --git a/oldtests/Lists/InBlockquote.html b/oldtests/Lists/InBlockquote.html
deleted file mode 100644
index da233e8..0000000
--- a/oldtests/Lists/InBlockquote.html
+++ /dev/null
@@ -1,22 +0,0 @@
-
    
-
      
-
    • tight
      • 
-
    • tight
      • 
-
    
-
    
-
    
-
      
-
    • loose
      • 
-
    • loose
      • 
-
    
-
    
-
    
-
      
-
    • one-item list
      • 
-
    
-
    
-
    
-
      
-
    • one-item list
      • 
-
    
-
    
diff --git a/oldtests/Lists/InBlockquote.markdown b/oldtests/Lists/InBlockquote.markdown
deleted file mode 100644
index 511563b..0000000
--- a/oldtests/Lists/InBlockquote.markdown
+++ /dev/null
@@ -1,12 +0,0 @@
-> - tight
-> - tight
-
-
-> - loose
->
-> - loose
-
-
-> - one-item list
-
-> - one-item list
diff --git a/oldtests/Lists/Indents.html b/oldtests/Lists/Indents.html
deleted file mode 100644
index a11a5a6..0000000
--- a/oldtests/Lists/Indents.html
+++ /dev/null
@@ -1,22 +0,0 @@
-
    
-
      
-
    • foo
      
-
      bar
      • 
-
    
-
    
-
      
-
    • one
      • 
-
    • two
      • 
-
    
-
      
-
    • one
      • 
-
    • two
      • 
-
    • three
      • 
-
    
-
      
-
    • one
-
        
-
      • two
        • 
-
      • 
-
    • three
      • 
-
    
diff --git a/oldtests/Lists/Indents.markdown b/oldtests/Lists/Indents.markdown
deleted file mode 100644
index 293d112..0000000
--- a/oldtests/Lists/Indents.markdown
+++ /dev/null
@@ -1,17 +0,0 @@
- > * foo
->
->   bar
-
-
-  - one
-  - two
-
-
-- one
- - two
-- three
-
-
-- one
-  - two
-- three
diff --git a/oldtests/Lists/ListsAndHRs.html b/oldtests/Lists/ListsAndHRs.html
deleted file mode 100644
index 40826f7..0000000
--- a/oldtests/Lists/ListsAndHRs.html
+++ /dev/null
@@ -1,7 +0,0 @@
-
      
-
    • item 1
-
        
-
      • item 2
        • 
-
      • 
-
    
-
    
diff --git a/oldtests/Lists/ListsAndHRs.markdown b/oldtests/Lists/ListsAndHRs.markdown
deleted file mode 100644
index 19c07e7..0000000
--- a/oldtests/Lists/ListsAndHRs.markdown
+++ /dev/null
@@ -1,3 +0,0 @@
-*   item 1
-    *   item 2
-*   *   *   *   *
diff --git a/oldtests/Lists/ListsAndSetextHeaders.html b/oldtests/Lists/ListsAndSetextHeaders.html
deleted file mode 100644
index c6af9eb..0000000
--- a/oldtests/Lists/ListsAndSetextHeaders.html
+++ /dev/null
@@ -1,6 +0,0 @@
-
      
-
    1. item
      2. 
-
    2. item
-Not header
      3. 
-
    
-
    
diff --git a/oldtests/Lists/ListsAndSetextHeaders.markdown b/oldtests/Lists/ListsAndSetextHeaders.markdown
deleted file mode 100644
index acfa655..0000000
--- a/oldtests/Lists/ListsAndSetextHeaders.markdown
+++ /dev/null
@@ -1,4 +0,0 @@
-1. item
-2. item
-Not header
-----------
diff --git a/oldtests/Lists/MultipleBlankLines.html b/oldtests/Lists/MultipleBlankLines.html
deleted file mode 100644
index d894db1..0000000
--- a/oldtests/Lists/MultipleBlankLines.html
+++ /dev/null
@@ -1,56 +0,0 @@
-
      
-
    1. First Item
      
-
        
-
      • one
        
-
          
-
        • two
          • 
-
        • 
-
      • one
        
-
          
-
        • two
          • 
-
        • 
-
      2. 
-
    2. Second Item
      
-
        
-
      • one
-
          
-
        • two
          • 
-
        • 
-
      3. 
-
    
-
      
-
    • one
-
        
-
      • two
        • 
-
      • 
-
    
-
      
-
    1. Third Item
      
-
        
-
      • one
-
          
-
        • two
          • 
-
        • 
-
      2. 
-
    
-
      
-
    • one
-
        
-
      • two
        • 
-
      • 
-
    
-
      
-
    1. Fourth Item
      
-
        
-
      • one
-
          
-
        • two
          • 
-
        • 
-
      2. 
-
    
-
      
-
    • one
-
        
-
      • two
        • 
-
      • 
-
    
diff --git a/oldtests/Lists/MultipleBlankLines.markdown b/oldtests/Lists/MultipleBlankLines.markdown
deleted file mode 100644
index e24a4f2..0000000
--- a/oldtests/Lists/MultipleBlankLines.markdown
+++ /dev/null
@@ -1,37 +0,0 @@
-1. First Item
-
-   * one
-     * two
-
-   * one
-     * two
-
-1. Second Item
-
-   * one
-     * two
-
-
-   * one
-     * two
-
-1. Third Item
-
-   * one
-     * two
-
-
-
-   * one
-     * two
-
-1. Fourth Item
-
-   * one
-     * two
-
-
-
-
-   * one
-     * two
diff --git a/oldtests/Lists/Start.html b/oldtests/Lists/Start.html
deleted file mode 100644
index 46e0550..0000000
--- a/oldtests/Lists/Start.html
+++ /dev/null
@@ -1,11 +0,0 @@
-
      
-
    1. this list starts with 4.
      2. 
-
    2. and continues
      3. 
-
    3. the continuation number is irrelevant.
      4. 
-
    
-
      
-
    1. a space odyssey
      2. 
-
    
-
      
-
    1. standard lists get no start attribute
      2. 
-
    
diff --git a/oldtests/Lists/Start.markdown b/oldtests/Lists/Start.markdown
deleted file mode 100644
index 175226f..0000000
--- a/oldtests/Lists/Start.markdown
+++ /dev/null
@@ -1,7 +0,0 @@
-4. this list starts with 4.
-5. and continues
-1. the continuation number is irrelevant.
-
-2001) a space odyssey
-
-1. standard lists get no start attribute
diff --git a/oldtests/Lists/Sublists.html b/oldtests/Lists/Sublists.html
deleted file mode 100644
index af62915..0000000
--- a/oldtests/Lists/Sublists.html
+++ /dev/null
@@ -1,49 +0,0 @@
-
    Four levels:
    
-
      
-
    • one
-
        
-
      • two
-
          
-
        • three
-
            
-
          • four
            • 
-
          • 
-
        • 
-
      • 
-
    
-
      
-
    1. one
-
        
-
      1. two
-
          
-
        1. three
-
            
-
          1. four
            2. 
-
          2. 
-
        2. 
-
      2. 
-
    
-
      
-
    1. one
-
        
-
      • two
-
          
-
        1. three
-
            
-
          • four
            • 
-
          2. 
-
        • 
-
      2. 
-
    
-
      
-
    • one
-
        
-
      • two
-
          
-
        1. three
-
            
-
          1. four
            2. 
-
          2. 
-
        • 
-
      • 
-
    
diff --git a/oldtests/Lists/Sublists.markdown b/oldtests/Lists/Sublists.markdown
deleted file mode 100644
index 9eced9e..0000000
--- a/oldtests/Lists/Sublists.markdown
+++ /dev/null
@@ -1,24 +0,0 @@
-Four levels:
-
-- one
-  - two
-    - three
-      - four
-
-
-1. one
-   1.  two
-       1.  three
-           1.  four
-
-
-1) one
-   -  two
-      1) three
-         - four
-
-
-- one
-  - two
-    1. three
-       1) four
diff --git a/oldtests/Lists/TightAndLoose.html b/oldtests/Lists/TightAndLoose.html
deleted file mode 100644
index 7792ebb..0000000
--- a/oldtests/Lists/TightAndLoose.html
+++ /dev/null
@@ -1,49 +0,0 @@
-
      
-
    1. tight
      2. 
-
    
-
      
-
    • tight
      • 
-
    • list
      • 
-
    
-
      
-
    • loose
      • 
-
    • list
      • 
-
    
-
      
-
    1. tight
      2. 
-
    2. list
      3. 
-
    
-
      
-
    1. loose
      2. 
-
    2. list
      3. 
-
    
-
      
-
    1. loose
      
-
        
-
      • sublist
        • 
-
      2. 
-
    
-
      
-
    1. tight
-
        
-
      • sublist
        • 
-
      2. 
-
    
-
      
-
    • tight
-
      
-
      blockquote
-and
      
-
      
-
      code
-
      • 
-
    • tight
      • 
-
    
-
      
-
    • tight
-
        
-
      • with loose
        • 
-
      • sublist
        • 
-
      • 
-
    • tight
      • 
-
    
diff --git a/oldtests/Lists/TightAndLoose.markdown b/oldtests/Lists/TightAndLoose.markdown
deleted file mode 100644
index 263a34c..0000000
--- a/oldtests/Lists/TightAndLoose.markdown
+++ /dev/null
@@ -1,45 +0,0 @@
-1. tight
-
-
-- tight
-- list
-
-
-- loose
-
-- list
-
-
-1. tight
-2. list
-
-
-1. loose
-
-2. list
-
-
-1. loose
-
-   - sublist
-
-
-
-1. tight
-   - sublist
-
-
-- tight
-  > blockquote
-  and
-  ```
-  code
-  ```
-- tight
-
-
-- tight
-  - with loose
-
-  - sublist
-- tight
diff --git a/oldtests/Lists/TightLooseBlockquote.html b/oldtests/Lists/TightLooseBlockquote.html
deleted file mode 100644
index 7e78214..0000000
--- a/oldtests/Lists/TightLooseBlockquote.html
+++ /dev/null
@@ -1,32 +0,0 @@
-
      
-
    • tight I
-
      
-
      bq
      
-
      • 
-
    • tight I
      • 
-
    
-
      
-
    • tight II
-
      
-
      bq
      
-
      
-foo
      • 
-
    • tight II
      • 
-
    
-
      
-
    1. Blank lines in bq don't break list
-
      
-
      bq
      
-
      2. 
-
    2. Should say (2) in output
      3. 
-
    
-
      
-
    • Blank lines in bq don't break LI
-
        
-
      • item A
-
        
-
        bq
        
-
        • 
-
      • item B
        • 
-
      • 
-
    
diff --git a/oldtests/Lists/TightLooseBlockquote.markdown b/oldtests/Lists/TightLooseBlockquote.markdown
deleted file mode 100644
index 08200cc..0000000
--- a/oldtests/Lists/TightLooseBlockquote.markdown
+++ /dev/null
@@ -1,25 +0,0 @@
-* tight I
-  > bq
-  >
-* tight I
-
-
-* tight II
-  > bq
-  >
-  foo
-* tight II
-
-1. Blank lines in bq don't break list
-   > bq
-   >
-   >
-1. Should say (2) in output
-
-* Blank lines in bq don't break LI
-  * item A
-    > bq
-    >
-    >
-  * item B
-  
\ No newline at end of file
diff --git a/oldtests/Lists/TightLooseMore.html b/oldtests/Lists/TightLooseMore.html
deleted file mode 100644
index f26f457..0000000
--- a/oldtests/Lists/TightLooseMore.html
+++ /dev/null
@@ -1,7 +0,0 @@
-
      
-
    • foo
      
-
        
-
      • bar
        • 
-
      
-
      blah
      • 
-
    
diff --git a/oldtests/Lists/TightLooseMore.markdown b/oldtests/Lists/TightLooseMore.markdown
deleted file mode 100644
index 7ace63f..0000000
--- a/oldtests/Lists/TightLooseMore.markdown
+++ /dev/null
@@ -1,4 +0,0 @@
-* foo
-  * bar
-
-  blah
\ No newline at end of file
diff --git a/oldtests/Lists/TwoBlankLinesEndList.html b/oldtests/Lists/TwoBlankLinesEndList.html
deleted file mode 100644
index 629add1..0000000
--- a/oldtests/Lists/TwoBlankLinesEndList.html
+++ /dev/null
@@ -1,21 +0,0 @@
-
      
-
    1. one
      2. 
-
    2. two
      3. 
-
    
-
      
-
    1. new list
      2. 
-
    
-
    
-
      
-
    • one
      • 
-
    • two
      • 
-
    
-
      
-
    • new list
      • 
-
    
-
    
-
      
-
    1. one
      2. 
-
    
-
    code
-
    
diff --git a/oldtests/Lists/TwoBlankLinesEndList.markdown b/oldtests/Lists/TwoBlankLinesEndList.markdown
deleted file mode 100644
index 2984a19..0000000
--- a/oldtests/Lists/TwoBlankLinesEndList.markdown
+++ /dev/null
@@ -1,20 +0,0 @@
-1. one
-
-2. two
-
-
-1. new list
-
-
-> - one
->
-> - two
->
->
-> - new list
-
-
-1.  one
-
-
-    code
diff --git a/oldtests/Makefile b/oldtests/Makefile
deleted file mode 100644
index c8a30bd..0000000
--- a/oldtests/Makefile
+++ /dev/null
@@ -1,55 +0,0 @@
-SHELL=/bin/bash
-TESTDIR ?= *
-PATT ?= .
-TESTS=$(shell ls $(TESTDIR)/*.markdown | grep $(PATT))
-DIFFS=$(patsubst %.markdown,%.diff,$(TESTS))
-PROG ?= ../stmd
-FILTER ?= perl -pe 's/ /␣/g'
-TIDYCMD ?= tidy -asxhtml -utf8 --show-body-only yes --show-warnings no -quiet
-DETAILS ?= 1
-
-# Check to see if echo supports -e option to allow backslash escapes
-ifeq ($(shell echo -e),-e)
-ECHO=echo
-else
-ECHO=echo -e
-endif
-
-all: $(DIFFS)
-	PASS=0;TESTS=0; \
-	for f in $(DIFFS); do \
-	  let TESTS=TESTS+1; \
-	  [ -s $$f ] || let PASS=PASS+1; \
-	done; \
-	$(ECHO)  "\033[1m$$PASS of $$TESTS tests passed.\033[0m"; \
-	if [ $$TESTS -eq $$PASS ]; then exit 0; else exit 1; fi
-
-%.actual.html: %.markdown
-ifeq ($(TIDY),1)
-	-cat $< | $(PROG) | $(TIDYCMD) > $@
-else
-	-cat $< | $(PROG) > $@
-endif
-
-%.expected.html: %.html
-ifeq ($(TIDY),1)
-	-$(TIDYCMD) $< > $@
-else
-	cp $< $@
-endif
-
-%.diff: %.expected.html %.actual.html
-	diff --unified=1 <(cat $(word 1,$^) | $(FILTER)) <(cat $(word 2,$^) | $(FILTER)) > $@ ; \
-	  if [ -s $@ ]; then \
-		$(ECHO)  "\033[1;31m✘ $(patsubst %.diff,%,$@)\033[0m"; \
-		if [ $(DETAILS) == "1" ]; then \
-			$(ECHO)  "\033[0;36m" ; cat $@; $(ECHO)  "\033[0m"; \
-		fi \
-	  else \
-		$(ECHO)  "\033[1;32m✓ $(patsubst %.diff,%,$@)\033[0m"; \
-	  fi
-
-.PHONY: all clean
-
-clean:
-	-@rm */*.{diff,actual.html,expected.html}
diff --git a/oldtests/Misc/BackslashEscapes.html b/oldtests/Misc/BackslashEscapes.html
deleted file mode 100644
index 3eb2aed..0000000
--- a/oldtests/Misc/BackslashEscapes.html
+++ /dev/null
@@ -1,14 +0,0 @@
-
    *not emphasized*
-\emphasis
-**not bold**
-<br/> not a tag
-[link](/foo) not a link
-link
-`not code`
    
-
    1. not a list item
    
-
    * not a list.
    
-
    # Not a header
    
-
    [foo]: /url "not a reference"
    
-
    $ ^ ; can be escaped.
-\a \b \T cannot.
-unicode letters and symbols cannot: \π \‥.
    
diff --git a/oldtests/Misc/BackslashEscapes.markdown b/oldtests/Misc/BackslashEscapes.markdown
deleted file mode 100644
index 23496dc..0000000
--- a/oldtests/Misc/BackslashEscapes.markdown
+++ /dev/null
@@ -1,19 +0,0 @@
-\*not emphasized*
-\\*emphasis*
-\*\*not bold**
-\
     not a tag
-\[link](/foo) not a link
-[link](/foo\) "title\"")
-\`not code`
-
-1\. not a list item
-
-\* not a list.
-
-\# Not a header
-
-\[foo]: /url "not a reference"
-
-\$ \^ \; can be escaped.
-\a \b \T cannot.
-unicode letters and symbols cannot: \π \‥.
diff --git a/oldtests/Misc/Laziness.html b/oldtests/Misc/Laziness.html
deleted file mode 100644
index e130eb5..0000000
--- a/oldtests/Misc/Laziness.html
+++ /dev/null
@@ -1,22 +0,0 @@
-
    
-
      
-
    1. one
-two
      2. 
-
    
-
    
-
    Laziness only affects paragraph continuations:
    
-
    
-
    code
-
    
-
    
-
    not same code block
-
    
-
      
-
    1. hello
      2. 
-
    
-
    
-
    
-
    
-
    
-
    code
    
-
    
diff --git a/oldtests/Misc/Laziness.markdown b/oldtests/Misc/Laziness.markdown
deleted file mode 100644
index 2c32870..0000000
--- a/oldtests/Misc/Laziness.markdown
+++ /dev/null
@@ -1,14 +0,0 @@
-> 1.  one
-> two
-
-Laziness only affects paragraph continuations:
-
->     code
-    not same code block
-
-1.    hello
------
-
-> ```
-code
-```
diff --git a/oldtests/Misc/LineBreaks.html b/oldtests/Misc/LineBreaks.html
deleted file mode 100644
index 2d85e85..0000000
--- a/oldtests/Misc/LineBreaks.html
+++ /dev/null
@@ -1,11 +0,0 @@
-
    Two spaces
    
-break a line. Or more than two
    
-and spaces in the following line are absorbed.
    
-
    You can also break lines with
    
-a backslash.
    
-
    Two spaces at the end of a paragraph are
-not a line break.
    
-
    A backslash at the end of a paragraph is
-not a line break.\
    
-
    Similarly with setext headers
    
-
    And with backslashes\
    
diff --git a/oldtests/Misc/LineBreaks.markdown b/oldtests/Misc/LineBreaks.markdown
deleted file mode 100644
index 3632dcb..0000000
--- a/oldtests/Misc/LineBreaks.markdown
+++ /dev/null
@@ -1,18 +0,0 @@
-Two spaces  
-break a line. Or more than two      
-  and spaces in the following line are absorbed.
-
-You can also break lines with\
-a backslash.
-
-Two spaces at the end of a paragraph are
-not a line break.  
-
-A backslash at the end of a paragraph is
-not a line break.\
-
-Similarly with setext headers   
--------------------------------
-
-And with backslashes\
----------------------
diff --git a/oldtests/Misc/Transitions.html b/oldtests/Misc/Transitions.html
deleted file mode 100644
index fceff9f..0000000
--- a/oldtests/Misc/Transitions.html
+++ /dev/null
@@ -1,26 +0,0 @@
-
    
-
    blockquote
    
-
    
-
    blockquote
    
-
    
-
    
-
      
-
    1. list
      2. 
-
    2. list
-
        
-
      • sublist
        • 
-
      3. 
-
    
-
    
-
    paragraph
    
-
    header
    
-
    header
    
-
    code
-
    
-
    code
-
    
-
    
- 
    
-# not a header
- 
    
-
    
diff --git a/oldtests/Misc/Transitions.markdown b/oldtests/Misc/Transitions.markdown
deleted file mode 100644
index 5f3a9d3..0000000
--- a/oldtests/Misc/Transitions.markdown
+++ /dev/null
@@ -1,20 +0,0 @@
-> blockquote
-> > blockquote
-1. list
-2. list
-   - sublist
-* * * * *
-paragraph
-
-header
-------
-### header
-    code
-```
-code
-```
-
    
- 
    
-# not a header
- 
    
-
    
diff --git a/oldtests/Original/Amps_and_angle_encoding.html b/oldtests/Original/Amps_and_angle_encoding.html
deleted file mode 100644
index fc1b2c3..0000000
--- a/oldtests/Original/Amps_and_angle_encoding.html
+++ /dev/null
@@ -1,9 +0,0 @@
-
    AT&T has an ampersand in their name.
    
-
    AT&T is another way to write it.
    
-
    This & that.
    
-
    4 < 5.
    
-
    6 > 5.
    
-
    Here's a link with an ampersand in the URL.
    
-
    Here's a link with an amersand in the link text: AT&T.
    
-
    Here's an inline link.
    
-
    Here's an inline link.
    
diff --git a/oldtests/Original/Amps_and_angle_encoding.markdown b/oldtests/Original/Amps_and_angle_encoding.markdown
deleted file mode 100644
index 0e9527f..0000000
--- a/oldtests/Original/Amps_and_angle_encoding.markdown
+++ /dev/null
@@ -1,21 +0,0 @@
-AT&T has an ampersand in their name.
-
-AT&T is another way to write it.
-
-This & that.
-
-4 < 5.
-
-6 > 5.
-
-Here's a [link] [1] with an ampersand in the URL.
-
-Here's a link with an amersand in the link text: [AT&T] [2].
-
-Here's an inline [link](/script?foo=1&bar=2).
-
-Here's an inline [link]().
-
-
-[1]: http://example.com/?foo=1&bar=2
-[2]: http://att.com/  "AT&T"
\ No newline at end of file
diff --git a/oldtests/Original/Auto_links.html b/oldtests/Original/Auto_links.html
deleted file mode 100644
index f517fe6..0000000
--- a/oldtests/Original/Auto_links.html
+++ /dev/null
@@ -1,13 +0,0 @@
-
    Link: http://example.com/.
    
-
    With an ampersand: http://example.com/?foo=1&bar=2
    
-
-
    
-
    Blockquoted: http://example.com/
    
-
    
-
    Auto-links should not occur here: <http://example.com/>
    
-
    or here: <http://example.com/>
-
    
diff --git a/oldtests/Original/Auto_links.markdown b/oldtests/Original/Auto_links.markdown
deleted file mode 100644
index abbc488..0000000
--- a/oldtests/Original/Auto_links.markdown
+++ /dev/null
@@ -1,13 +0,0 @@
-Link: .
-
-With an ampersand: 
-
-* In a list?
-* 
-* It should.
-
-> Blockquoted: 
-
-Auto-links should not occur here: ``
-
-	or here: 
\ No newline at end of file
diff --git a/oldtests/Original/Backslash_escapes.html b/oldtests/Original/Backslash_escapes.html
deleted file mode 100644
index 9a83379..0000000
--- a/oldtests/Original/Backslash_escapes.html
+++ /dev/null
@@ -1,75 +0,0 @@
-
    These should all get escaped:
    
-
    Backslash: \
    
-
    Backtick: `
    
-
    Asterisk: *
    
-
    Underscore: _
    
-
    Left brace: {
    
-
    Right brace: }
    
-
    Left bracket: [
    
-
    Right bracket: ]
    
-
    Left paren: (
    
-
    Right paren: )
    
-
    Greater-than: >
    
-
    Hash: #
    
-
    Period: .
    
-
    Bang: !
    
-
    Plus: +
    
-
    Minus: -
    
-
    These should not, because they occur within a code block:
    
-
    Backslash: \\
-
-Backtick: \`
-
-Asterisk: \*
-
-Underscore: \_
-
-Left brace: \{
-
-Right brace: \}
-
-Left bracket: \[
-
-Right bracket: \]
-
-Left paren: \(
-
-Right paren: \)
-
-Greater-than: \>
-
-Hash: \#
-
-Period: \.
-
-Bang: \!
-
-Plus: \+
-
-Minus: \-
-
    
-
    Nor should these, which occur in code spans:
    
-
    Backslash: \\
    
-
    Backtick: \`
    
-
    Asterisk: \*
    
-
    Underscore: \_
    
-
    Left brace: \{
    
-
    Right brace: \}
    
-
    Left bracket: \[
    
-
    Right bracket: \]
    
-
    Left paren: \(
    
-
    Right paren: \)
    
-
    Greater-than: \>
    
-
    Hash: \#
    
-
    Period: \.
    
-
    Bang: \!
    
-
    Plus: \+
    
-
    Minus: \-
    
-
    These should get escaped, even though they're matching pairs for
-other Markdown constructs:
    
-
    *asterisks*
    
-
    _underscores_
    
-
    `backticks`
    
-
    This is a code span with a literal backslash-backtick sequence: \`
    
-
    This is a tag with unescaped backticks bar.
    
-
    This is a tag with backslashes bar.
    
diff --git a/oldtests/Original/Backslash_escapes.markdown b/oldtests/Original/Backslash_escapes.markdown
deleted file mode 100644
index 5b014cb..0000000
--- a/oldtests/Original/Backslash_escapes.markdown
+++ /dev/null
@@ -1,120 +0,0 @@
-These should all get escaped:
-
-Backslash: \\
-
-Backtick: \`
-
-Asterisk: \*
-
-Underscore: \_
-
-Left brace: \{
-
-Right brace: \}
-
-Left bracket: \[
-
-Right bracket: \]
-
-Left paren: \(
-
-Right paren: \)
-
-Greater-than: \>
-
-Hash: \#
-
-Period: \.
-
-Bang: \!
-
-Plus: \+
-
-Minus: \-
-
-
-
-These should not, because they occur within a code block:
-
-	Backslash: \\
-
-	Backtick: \`
-
-	Asterisk: \*
-
-	Underscore: \_
-
-	Left brace: \{
-
-	Right brace: \}
-
-	Left bracket: \[
-
-	Right bracket: \]
-
-	Left paren: \(
-
-	Right paren: \)
-
-	Greater-than: \>
-
-	Hash: \#
-
-	Period: \.
-
-	Bang: \!
-
-	Plus: \+
-
-	Minus: \-
-
-
-Nor should these, which occur in code spans:
-
-Backslash: `\\`
-
-Backtick: `` \` ``
-
-Asterisk: `\*`
-
-Underscore: `\_`
-
-Left brace: `\{`
-
-Right brace: `\}`
-
-Left bracket: `\[`
-
-Right bracket: `\]`
-
-Left paren: `\(`
-
-Right paren: `\)`
-
-Greater-than: `\>`
-
-Hash: `\#`
-
-Period: `\.`
-
-Bang: `\!`
-
-Plus: `\+`
-
-Minus: `\-`
-
-
-These should get escaped, even though they're matching pairs for
-other Markdown constructs:
-
-\*asterisks\*
-
-\_underscores\_
-
-\`backticks\`
-
-This is a code span with a literal backslash-backtick sequence: `` \` ``
-
-This is a tag with unescaped backticks bar.
-
-This is a tag with backslashes bar.
diff --git a/oldtests/Original/Blockquotes_with_code_blocks.html b/oldtests/Original/Blockquotes_with_code_blocks.html
deleted file mode 100644
index fd1cb1b..0000000
--- a/oldtests/Original/Blockquotes_with_code_blocks.html
+++ /dev/null
@@ -1,12 +0,0 @@
-
    
-
    Example:
    
-
    sub status {
-    print "working";
-}
-
    
-
    Or:
    
-
    sub status {
-    return "working";
-}
-
    
-
    
diff --git a/oldtests/Original/Blockquotes_with_code_blocks.markdown b/oldtests/Original/Blockquotes_with_code_blocks.markdown
deleted file mode 100644
index c31d171..0000000
--- a/oldtests/Original/Blockquotes_with_code_blocks.markdown
+++ /dev/null
@@ -1,11 +0,0 @@
-> Example:
-> 
->     sub status {
->         print "working";
->     }
-> 
-> Or:
-> 
->     sub status {
->         return "working";
->     }
diff --git a/oldtests/Original/Code_Blocks.html b/oldtests/Original/Code_Blocks.html
deleted file mode 100644
index 7d89615..0000000
--- a/oldtests/Original/Code_Blocks.html
+++ /dev/null
@@ -1,12 +0,0 @@
-
    code block on the first line
-
    
-
    Regular text.
    
-
    code block indented by spaces
-
    
-
    Regular text.
    
-
    the lines in this block  
-all contain trailing spaces  
-
    
-
    Regular Text.
    
-
    code block on the last line
-
    
diff --git a/oldtests/Original/Code_Blocks.markdown b/oldtests/Original/Code_Blocks.markdown
deleted file mode 100644
index b54b092..0000000
--- a/oldtests/Original/Code_Blocks.markdown
+++ /dev/null
@@ -1,14 +0,0 @@
-	code block on the first line
-	
-Regular text.
-
-    code block indented by spaces
-
-Regular text.
-
-	the lines in this block  
-	all contain trailing spaces  
-
-Regular Text.
-
-	code block on the last line
\ No newline at end of file
diff --git a/oldtests/Original/Code_Spans.html b/oldtests/Original/Code_Spans.html
deleted file mode 100644
index 27acea1..0000000
--- a/oldtests/Original/Code_Spans.html
+++ /dev/null
@@ -1,3 +0,0 @@
-
    <test a=" content of attribute ">
    
-
    Fix for backticks within HTML tag: like this
    
-
    Here's how you put `backticks` in a code span.
    
diff --git a/oldtests/Original/Code_Spans.markdown b/oldtests/Original/Code_Spans.markdown
deleted file mode 100644
index 5c229c7..0000000
--- a/oldtests/Original/Code_Spans.markdown
+++ /dev/null
@@ -1,5 +0,0 @@
-``
-
-Fix for backticks within HTML tag: like this
-
-Here's how you put `` `backticks` `` in a code span.
\ No newline at end of file
diff --git a/oldtests/Original/Horizontal_rules.html b/oldtests/Original/Horizontal_rules.html
deleted file mode 100644
index a89efdb..0000000
--- a/oldtests/Original/Horizontal_rules.html
+++ /dev/null
@@ -1,39 +0,0 @@
-
    Dashes:
    
-
    
-
    
-
    
-
    
-
    ---
-
    
-
    
-
    
-
    
-
    
-
    - - -
-
    
-
    Asterisks:
    
-
    
-
    
-
    
-
    
-
    ***
-
    
-
    
-
    
-
    
-
    
-
    * * *
-
    
-
    Underscores:
    
-
    
-
    
-
    
-
    
-
    ___
-
    
-
    
-
    
-
    
-
    
-
    _ _ _
-
    
diff --git a/oldtests/Original/Horizontal_rules.markdown b/oldtests/Original/Horizontal_rules.markdown
deleted file mode 100644
index 1594bda..0000000
--- a/oldtests/Original/Horizontal_rules.markdown
+++ /dev/null
@@ -1,67 +0,0 @@
-Dashes:
-
----
-
- ---
- 
-  ---
-
-   ---
-
-	---
-
-- - -
-
- - - -
- 
-  - - -
-
-   - - -
-
-	- - -
-
-
-Asterisks:
-
-***
-
- ***
- 
-  ***
-
-   ***
-
-	***
-
-* * *
-
- * * *
- 
-  * * *
-
-   * * *
-
-	* * *
-
-
-Underscores:
-
-___
-
- ___
- 
-  ___
-
-   ___
-
-    ___
-
-_ _ _
-
- _ _ _
- 
-  _ _ _
-
-   _ _ _
-
-    _ _ _
diff --git a/oldtests/Original/Images.html b/oldtests/Original/Images.html
deleted file mode 100644
index bd5a7e0..0000000
--- a/oldtests/Original/Images.html
+++ /dev/null
@@ -1,11 +0,0 @@
-
    Alt text
    
-
    Alt text
    
-
    Inline within a paragraph: alt text.
    
-
    alt text
    
-
    alt text
    
-
    alt text
    
-
    alt text.
    
-
    Empty
    
-
    this is a stupid URL
    
-
    alt text
    
-
    alt text
    
diff --git a/oldtests/Original/Images.markdown b/oldtests/Original/Images.markdown
deleted file mode 100644
index 5707590..0000000
--- a/oldtests/Original/Images.markdown
+++ /dev/null
@@ -1,26 +0,0 @@
-![Alt text](/path/to/img.jpg)
-
-![Alt text](/path/to/img.jpg "Optional title")
-
-Inline within a paragraph: [alt text](/url/).
-
-![alt text](/url/  "title preceded by two spaces")
-
-![alt text](/url/  "title has spaces afterward"  )
-
-![alt text]()
-
-![alt text]( "with a title").
-
-![Empty]()
-
-![this is a stupid URL](http://example.com/(parens).jpg)
-
-
-![alt text][foo]
-
-  [foo]: /url/
-
-![alt text][bar]
-
-  [bar]: /url/ "Title here"
\ No newline at end of file
diff --git a/oldtests/Original/Inline_HTML_Advanced.html b/oldtests/Original/Inline_HTML_Advanced.html
deleted file mode 100644
index 631c135..0000000
--- a/oldtests/Original/Inline_HTML_Advanced.html
+++ /dev/null
@@ -1,23 +0,0 @@
-
    Simple block on one line:
    
-
    foo
    
-
    And nested without indentation:
    
-
    
-
    
-
    
-foo
-
    
-
    
-
    
-
    bar
    
-
    
-
    And with attributes:
    
-
    
-    
    
-    
    
-
    
-
    This was broken in 1.0.2b7:
    
-
    
-
    
-foo
-
    
-
    
diff --git a/oldtests/Original/Inline_HTML_Advanced.markdown b/oldtests/Original/Inline_HTML_Advanced.markdown
deleted file mode 100644
index 3633f81..0000000
--- a/oldtests/Original/Inline_HTML_Advanced.markdown
+++ /dev/null
@@ -1,30 +0,0 @@
-Simple block on one line:
-
-
    foo
    
-
-And nested without indentation:
-
-
    
-
    
-
    
-foo
-
    
-
    
-
    
-
    bar
    
-
    
-
-And with attributes:
-
-
    
-	
    
-	
    
-
    
-
-This was broken in 1.0.2b7:
-
-
    
-
    
-foo
-
    
-
    
diff --git a/oldtests/Original/Inline_HTML_Simple.html b/oldtests/Original/Inline_HTML_Simple.html
deleted file mode 100644
index 923a18c..0000000
--- a/oldtests/Original/Inline_HTML_Simple.html
+++ /dev/null
@@ -1,45 +0,0 @@
-
    Here's a simple block:
    
-
    
-    foo
-
    
-
    This should be a code block, though:
    
-
    <div>
-    foo
-</div>
-
    
-
    As should this:
    
-
    <div>foo</div>
-
    
-
    Now, nested:
    
-
    
-    
    
-        
    
-            foo
-        
    
-    
    
-
    
-
    This should just be an HTML comment:
    
-
-
    Multiline:
    
-
-
    Code block:
    
-
    <!-- Comment -->
-
    
-
    Just plain comment, with trailing spaces on the line:
    
-   
-
    Code:
    
-
    <hr />
-
    
-
    Hr's:
    
-
    
-
    
-
    
-
       
-
      
-
     
-
    
-
    
-
    
diff --git a/oldtests/Original/Inline_HTML_Simple.markdown b/oldtests/Original/Inline_HTML_Simple.markdown
deleted file mode 100644
index 14aa2dc..0000000
--- a/oldtests/Original/Inline_HTML_Simple.markdown
+++ /dev/null
@@ -1,69 +0,0 @@
-Here's a simple block:
-
-
    
-	foo
-
    
-
-This should be a code block, though:
-
-	
    
-		foo
-	
    
-
-As should this:
-
-	
    foo
    
-
-Now, nested:
-
-
    
-	
    
-		
    
-			foo
-		
    
-	
    
-
    
-
-This should just be an HTML comment:
-
-
-
-Multiline:
-
-
-
-Code block:
-
-	
-
-Just plain comment, with trailing spaces on the line:
-
-   
-
-Code:
-
-	
    
-	
-Hr's:
-
-
    
-
-
    
-
-
    
-
-
       
-
-
      
-
-
     
-
-
    
-
-
    
-
-
    
-
diff --git a/oldtests/Original/Inline_HTML_comments.html b/oldtests/Original/Inline_HTML_comments.html
deleted file mode 100644
index ebc4818..0000000
--- a/oldtests/Original/Inline_HTML_comments.html
+++ /dev/null
@@ -1,8 +0,0 @@
-
    Paragraph one.
    
-
-
-
    Paragraph two.
    
-
-
    The end.
    
diff --git a/oldtests/Original/Inline_HTML_comments.markdown b/oldtests/Original/Inline_HTML_comments.markdown
deleted file mode 100644
index 41d830d..0000000
--- a/oldtests/Original/Inline_HTML_comments.markdown
+++ /dev/null
@@ -1,13 +0,0 @@
-Paragraph one.
-
-
-
-
-
-Paragraph two.
-
-
-
-The end.
diff --git a/oldtests/Original/Links_inline_style.html b/oldtests/Original/Links_inline_style.html
deleted file mode 100644
index feb4637..0000000
--- a/oldtests/Original/Links_inline_style.html
+++ /dev/null
@@ -1,12 +0,0 @@
-
    Just a URL.
    
-
    URL and title.
    
-
    URL and title.
    
-
    URL and title.
    
-
    URL and title.
    
-
    URL wrapped in angle brackets.
    
-
    URL w/ angle brackets + title.
    
-
    Empty.
    
-
    With parens in the URL
    
-
    (With outer parens and parens in url)
    
-
    With parens in the URL
    
-
    (With outer parens and parens in url)
    
diff --git a/oldtests/Original/Links_inline_style.markdown b/oldtests/Original/Links_inline_style.markdown
deleted file mode 100644
index aba9658..0000000
--- a/oldtests/Original/Links_inline_style.markdown
+++ /dev/null
@@ -1,24 +0,0 @@
-Just a [URL](/url/).
-
-[URL and title](/url/ "title").
-
-[URL and title](/url/  "title preceded by two spaces").
-
-[URL and title](/url/	"title preceded by a tab").
-
-[URL and title](/url/ "title has spaces afterward"  ).
-
-[URL wrapped in angle brackets]().
-
-[URL w/ angle brackets + title]( "Here's the title").
-
-[Empty]().
-
-[With parens in the URL](http://en.wikipedia.org/wiki/WIMP_(computing))
-
-(With outer parens and [parens in url](/foo(bar)))
-
-
-[With parens in the URL](/foo(bar) "and a title")
-
-(With outer parens and [parens in url](/foo(bar) "and a title"))
diff --git a/oldtests/Original/Links_reference_style.html b/oldtests/Original/Links_reference_style.html
deleted file mode 100644
index 6d78b96..0000000
--- a/oldtests/Original/Links_reference_style.html
+++ /dev/null
@@ -1,28 +0,0 @@
-
    Foo bar.
    
-
    Foo bar.
    
-
    Foo bar.
    
-
    With embedded [brackets].
    
-
    Indented once.
    
-
    Indented twice.
    
-
    Indented thrice.
    
-
    Indented [four][] times.
    
-
    [four]: /url
-
    
-
    
-
    this should work
    
-
    So should this.
    
-
    And this.
    
-
    And this.
    
-
    And this.
    
-
    But not [that] [].
    
-
    Nor [that][].
    
-
    Nor [that].
    
-
    [Something in brackets like this should work]
    
-
    [Same with this.]
    
-
    In this case, this points to something else.
    
-
    Backslashing should suppress [this] and [this].
    
-
    
-
    Here's one where the link
-breaks across lines.
    
-
    Here's another where the link
-breaks across lines, but with a line-ending space.
    
diff --git a/oldtests/Original/Links_reference_style.markdown b/oldtests/Original/Links_reference_style.markdown
deleted file mode 100644
index 341ec88..0000000
--- a/oldtests/Original/Links_reference_style.markdown
+++ /dev/null
@@ -1,71 +0,0 @@
-Foo [bar] [1].
-
-Foo [bar][1].
-
-Foo [bar]
-[1].
-
-[1]: /url/  "Title"
-
-
-With [embedded [brackets]] [b].
-
-
-Indented [once][].
-
-Indented [twice][].
-
-Indented [thrice][].
-
-Indented [four][] times.
-
- [once]: /url
-
-  [twice]: /url
-
-   [thrice]: /url
-
-    [four]: /url
-
-
-[b]: /url/
-
-* * *
-
-[this] [this] should work
-
-So should [this][this].
-
-And [this] [].
-
-And [this][].
-
-And [this].
-
-But not [that] [].
-
-Nor [that][].
-
-Nor [that].
-
-[Something in brackets like [this][] should work]
-
-[Same with [this].]
-
-In this case, [this](/somethingelse/) points to something else.
-
-Backslashing should suppress \[this] and [this\].
-
-[this]: foo
-
-
-* * *
-
-Here's one where the [link
-breaks] across lines.
-
-Here's another where the [link 
-breaks] across lines, but with a line-ending space.
-
-
-[link breaks]: /url/
diff --git a/oldtests/Original/Links_shortcut_references.html b/oldtests/Original/Links_shortcut_references.html
deleted file mode 100644
index 8163ade..0000000
--- a/oldtests/Original/Links_shortcut_references.html
+++ /dev/null
@@ -1,6 +0,0 @@
-
    This is the simple case.
    
-
    This one has a line
-break.
    
-
    This one has a line
-break with a line-ending space.
    
-
    this and the other
    
diff --git a/oldtests/Original/Links_shortcut_references.markdown b/oldtests/Original/Links_shortcut_references.markdown
deleted file mode 100644
index 8c44c98..0000000
--- a/oldtests/Original/Links_shortcut_references.markdown
+++ /dev/null
@@ -1,20 +0,0 @@
-This is the [simple case].
-
-[simple case]: /simple
-
-
-
-This one has a [line
-break].
-
-This one has a [line 
-break] with a line-ending space.
-
-[line break]: /foo
-
-
-[this] [that] and the [other]
-
-[this]: /this
-[that]: /that
-[other]: /other
diff --git a/oldtests/Original/Literal_quotes_in_titles.html b/oldtests/Original/Literal_quotes_in_titles.html
deleted file mode 100644
index 62e8641..0000000
--- a/oldtests/Original/Literal_quotes_in_titles.html
+++ /dev/null
@@ -1,2 +0,0 @@
-
    Foo bar.
    
-
    Foo bar.
    
diff --git a/oldtests/Original/Literal_quotes_in_titles.markdown b/oldtests/Original/Literal_quotes_in_titles.markdown
deleted file mode 100644
index 29d0e42..0000000
--- a/oldtests/Original/Literal_quotes_in_titles.markdown
+++ /dev/null
@@ -1,7 +0,0 @@
-Foo [bar][].
-
-Foo [bar](/url/ "Title with "quotes" inside").
-
-
-  [bar]: /url/ "Title with "quotes" inside"
-
diff --git a/oldtests/Original/Markdown_Documentation_Basics.html b/oldtests/Original/Markdown_Documentation_Basics.html
deleted file mode 100644
index 0dee67f..0000000
--- a/oldtests/Original/Markdown_Documentation_Basics.html
+++ /dev/null
@@ -1,242 +0,0 @@
-
    Markdown: Basics
    
-
-
    Getting the Gist of Markdown's Formatting Syntax
    
-
    This page offers a brief overview of what it's like to use Markdown.
-The syntax page provides complete, detailed documentation for
-every feature, but Markdown should be very easy to pick up simply by
-looking at a few examples of it in action. The examples on this page
-are written in a before/after style, showing example syntax and the
-HTML output produced by Markdown.
    
-
    It's also helpful to simply try Markdown out; the Dingus is a
-web application that allows you type your own Markdown-formatted text
-and translate it to XHTML.
    
-
    Note: This document is itself written using Markdown; you
-can see the source for it by adding '.text' to the URL.
    
-
    Paragraphs, Headers, Blockquotes
    
-
    A paragraph is simply one or more consecutive lines of text, separated
-by one or more blank lines. (A blank line is any line that looks like a
-blank line -- a line containing nothing spaces or tabs is considered
-blank.) Normal paragraphs should not be intended with spaces or tabs.
    
-
    Markdown offers two styles of headers: Setext and atx.
-Setext-style headers for <h1> and <h2> are created by
-"underlining" with equal signs (=) and hyphens (-), respectively.
-To create an atx-style header, you put 1-6 hash marks (#) at the
-beginning of the line -- the number of hashes equals the resulting
-HTML header level.
    
-
    Blockquotes are indicated using email-style '>' angle brackets.
    
-
    Markdown:
    
-
    A First Level Header
-====================
-
-A Second Level Header
----------------------
-
-Now is the time for all good men to come to
-the aid of their country. This is just a
-regular paragraph.
-
-The quick brown fox jumped over the lazy
-dog's back.
-
-### Header 3
-
-> This is a blockquote.
->
-> This is the second paragraph in the blockquote.
->
-> ## This is an H2 in a blockquote
-
    
-
    Output:
    
-
    <h1>A First Level Header</h1>
-
-<h2>A Second Level Header</h2>
-
-<p>Now is the time for all good men to come to
-the aid of their country. This is just a
-regular paragraph.</p>
-
-<p>The quick brown fox jumped over the lazy
-dog's back.</p>
-
-<h3>Header 3</h3>
-
-<blockquote>
-    <p>This is a blockquote.</p>
-
-    <p>This is the second paragraph in the blockquote.</p>
-
-    <h2>This is an H2 in a blockquote</h2>
-</blockquote>
-
    
-
    Phrase Emphasis
    
-
    Markdown uses asterisks and underscores to indicate spans of emphasis.
    
-
    Markdown:
    
-
    Some of these words *are emphasized*.
-Some of these words _are emphasized also_.
-
-Use two asterisks for **strong emphasis**.
-Or, if you prefer, __use two underscores instead__.
-
    
-
    Output:
    
-
    <p>Some of these words <em>are emphasized</em>.
-Some of these words <em>are emphasized also</em>.</p>
-
-<p>Use two asterisks for <strong>strong emphasis</strong>.
-Or, if you prefer, <strong>use two underscores instead</strong>.</p>
-
    
-
    Lists
    
-
    Unordered (bulleted) lists use asterisks, pluses, and hyphens (*,
-+, and -) as list markers. These three markers are
-interchangable; this:
    
-
    *   Candy.
-*   Gum.
-*   Booze.
-
    
-
    this:
    
-
    +   Candy.
-+   Gum.
-+   Booze.
-
    
-
    and this:
    
-
    -   Candy.
--   Gum.
--   Booze.
-
    
-
    all produce the same output:
    
-
    <ul>
-<li>Candy.</li>
-<li>Gum.</li>
-<li>Booze.</li>
-</ul>
-
    
-
    Ordered (numbered) lists use regular numbers, followed by periods, as
-list markers:
    
-
    1.  Red
-2.  Green
-3.  Blue
-
    
-
    Output:
    
-
    <ol>
-<li>Red</li>
-<li>Green</li>
-<li>Blue</li>
-</ol>
-
    
-
    If you put blank lines between items, you'll get <p> tags for the
-list item text. You can create multi-paragraph list items by indenting
-the paragraphs by 4 spaces or 1 tab:
    
-
    *   A list item.
-
-    With multiple paragraphs.
-
-*   Another item in the list.
-
    
-
    Output:
    
-
    <ul>
-<li><p>A list item.</p>
-<p>With multiple paragraphs.</p></li>
-<li><p>Another item in the list.</p></li>
-</ul>
-
    
-
    Links
    
-
    Markdown supports two styles for creating links: inline and
-reference. With both styles, you use square brackets to delimit the
-text you want to turn into a link.
    
-
    Inline-style links use parentheses immediately after the link text.
-For example:
    
-
    This is an [example link](http://example.com/).
-
    
-
    Output:
    
-
    <p>This is an <a href="http://example.com/">
-example link</a>.</p>
-
    
-
    Optionally, you may include a title attribute in the parentheses:
    
-
    This is an [example link](http://example.com/ "With a Title").
-
    
-
    Output:
    
-
    <p>This is an <a href="http://example.com/" title="With a Title">
-example link</a>.</p>
-
    
-
    Reference-style links allow you to refer to your links by names, which
-you define elsewhere in your document:
    
-
    I get 10 times more traffic from [Google][1] than from
-[Yahoo][2] or [MSN][3].
-
-[1]: http://google.com/        "Google"
-[2]: http://search.yahoo.com/  "Yahoo Search"
-[3]: http://search.msn.com/    "MSN Search"
-
    
-
    Output:
    
-
    <p>I get 10 times more traffic from <a href="http://google.com/"
-title="Google">Google</a> than from <a href="http://search.yahoo.com/"
-title="Yahoo Search">Yahoo</a> or <a href="http://search.msn.com/"
-title="MSN Search">MSN</a>.</p>
-
    
-
    The title attribute is optional. Link names may contain letters,
-numbers and spaces, but are not case sensitive:
    
-
    I start my morning with a cup of coffee and
-[The New York Times][NY Times].
-
-[ny times]: http://www.nytimes.com/
-
    
-
    Output:
    
-
    <p>I start my morning with a cup of coffee and
-<a href="http://www.nytimes.com/">The New York Times</a>.</p>
-
    
-
    Images
    
-
    Image syntax is very much like link syntax.
    
-
    Inline (titles are optional):
    
-
    ![alt text](/path/to/img.jpg "Title")
-
    
-
    Reference-style:
    
-
    ![alt text][id]
-
-[id]: /path/to/img.jpg "Title"
-
    
-
    Both of the above examples produce the same output:
    
-
    <img src="/path/to/img.jpg" alt="alt text" title="Title" />
-
    
-
    Code
    
-
    In a regular paragraph, you can create code span by wrapping text in
-backtick quotes. Any ampersands (&) and angle brackets (< or
->) will automatically be translated into HTML entities. This makes
-it easy to use Markdown to write about HTML example code:
    
-
    I strongly recommend against using any `<blink>` tags.
-
-I wish SmartyPants used named entities like `&mdash;`
-instead of decimal-encoded entites like `&#8212;`.
-
    
-
    Output:
    
-
    <p>I strongly recommend against using any
-<code>&lt;blink&gt;</code> tags.</p>
-
-<p>I wish SmartyPants used named entities like
-<code>&amp;mdash;</code> instead of decimal-encoded
-entites like <code>&amp;#8212;</code>.</p>
-
    
-
    To specify an entire block of pre-formatted code, indent every line of
-the block by 4 spaces or 1 tab. Just like with code spans, &, <,
-and > characters will be escaped automatically.
    
-
    Markdown:
    
-
    If you want your page to validate under XHTML 1.0 Strict,
-you've got to put paragraph tags in your blockquotes:
-
-    <blockquote>
-        <p>For example.</p>
-    </blockquote>
-
    
-
    Output:
    
-
    <p>If you want your page to validate under XHTML 1.0 Strict,
-you've got to put paragraph tags in your blockquotes:</p>
-
-<pre><code>&lt;blockquote&gt;
-    &lt;p&gt;For example.&lt;/p&gt;
-&lt;/blockquote&gt;
-</code></pre>
-
    
diff --git a/oldtests/Original/Markdown_Documentation_Basics.markdown b/oldtests/Original/Markdown_Documentation_Basics.markdown
deleted file mode 100644
index 24eba65..0000000
--- a/oldtests/Original/Markdown_Documentation_Basics.markdown
+++ /dev/null
@@ -1,306 +0,0 @@
-Markdown: Basics
-================
-
-
-
-
-Getting the Gist of Markdown's Formatting Syntax
-------------------------------------------------
-
-This page offers a brief overview of what it's like to use Markdown.
-The [syntax page] [s] provides complete, detailed documentation for
-every feature, but Markdown should be very easy to pick up simply by
-looking at a few examples of it in action. The examples on this page
-are written in a before/after style, showing example syntax and the
-HTML output produced by Markdown.
-
-It's also helpful to simply try Markdown out; the [Dingus] [d] is a
-web application that allows you type your own Markdown-formatted text
-and translate it to XHTML.
-
-**Note:** This document is itself written using Markdown; you
-can [see the source for it by adding '.text' to the URL] [src].
-
-  [s]: /projects/markdown/syntax  "Markdown Syntax"
-  [d]: /projects/markdown/dingus  "Markdown Dingus"
-  [src]: /projects/markdown/basics.text
-
-
-## Paragraphs, Headers, Blockquotes ##
-
-A paragraph is simply one or more consecutive lines of text, separated
-by one or more blank lines. (A blank line is any line that looks like a
-blank line -- a line containing nothing spaces or tabs is considered
-blank.) Normal paragraphs should not be intended with spaces or tabs.
-
-Markdown offers two styles of headers: *Setext* and *atx*.
-Setext-style headers for `
    ` and `
    ` are created by
-"underlining" with equal signs (`=`) and hyphens (`-`), respectively.
-To create an atx-style header, you put 1-6 hash marks (`#`) at the
-beginning of the line -- the number of hashes equals the resulting
-HTML header level.
-
-Blockquotes are indicated using email-style '`>`' angle brackets.
-
-Markdown:
-
-    A First Level Header
-    ====================
-    
-    A Second Level Header
-    ---------------------
-
-    Now is the time for all good men to come to
-    the aid of their country. This is just a
-    regular paragraph.
-
-    The quick brown fox jumped over the lazy
-    dog's back.
-    
-    ### Header 3
-
-    > This is a blockquote.
-    >
-    > This is the second paragraph in the blockquote.
-    >
-    > ## This is an H2 in a blockquote
-
-
-Output:
-
-    
    A First Level Header
    
-    
-    
    A Second Level Header
    
-    
-    
    Now is the time for all good men to come to
-    the aid of their country. This is just a
-    regular paragraph.
    
-    
-    
    The quick brown fox jumped over the lazy
-    dog's back.
    
-    
-    
    Header 3
    
-    
-    
    
-        
    This is a blockquote.
    
-    
-        
    This is the second paragraph in the blockquote.
    
-    
-        
    This is an H2 in a blockquote
    
-    
    
-
-
-
-### Phrase Emphasis ###
-
-Markdown uses asterisks and underscores to indicate spans of emphasis.
-
-Markdown:
-
-    Some of these words *are emphasized*.
-    Some of these words _are emphasized also_.
-    
-    Use two asterisks for **strong emphasis**.
-    Or, if you prefer, __use two underscores instead__.
-
-Output:
-
-    
    Some of these words are emphasized.
-    Some of these words are emphasized also.
    
-    
-    
    Use two asterisks for strong emphasis.
-    Or, if you prefer, use two underscores instead.
    
-   
-
-
-## Lists ##
-
-Unordered (bulleted) lists use asterisks, pluses, and hyphens (`*`,
-`+`, and `-`) as list markers. These three markers are
-interchangable; this:
-
-    *   Candy.
-    *   Gum.
-    *   Booze.
-
-this:
-
-    +   Candy.
-    +   Gum.
-    +   Booze.
-
-and this:
-
-    -   Candy.
-    -   Gum.
-    -   Booze.
-
-all produce the same output:
-
-    
      
-    
    • Candy.
      • 
-    
    • Gum.
      • 
-    
    • Booze.
      • 
-    
    
-
-Ordered (numbered) lists use regular numbers, followed by periods, as
-list markers:
-
-    1.  Red
-    2.  Green
-    3.  Blue
-
-Output:
-
-    
      
-    
    1. Red
      2. 
-    
    2. Green
      3. 
-    
    3. Blue
      4. 
-    
    
-
-If you put blank lines between items, you'll get `
    ` tags for the
-list item text. You can create multi-paragraph list items by indenting
-the paragraphs by 4 spaces or 1 tab:
-
-    *   A list item.
-    
-        With multiple paragraphs.
-
-    *   Another item in the list.
-
-Output:
-
-    
      
-    
    • A list item.
      
-    
      With multiple paragraphs.
      • 
-    
    • Another item in the list.
      • 
-    
    
-    
-
-
-### Links ###
-
-Markdown supports two styles for creating links: *inline* and
-*reference*. With both styles, you use square brackets to delimit the
-text you want to turn into a link.
-
-Inline-style links use parentheses immediately after the link text.
-For example:
-
-    This is an [example link](http://example.com/).
-
-Output:
-
-    
    This is an 
-    example link.
    
-
-Optionally, you may include a title attribute in the parentheses:
-
-    This is an [example link](http://example.com/ "With a Title").
-
-Output:
-
-    
    This is an 
-    example link.
    
-
-Reference-style links allow you to refer to your links by names, which
-you define elsewhere in your document:
-
-    I get 10 times more traffic from [Google][1] than from
-    [Yahoo][2] or [MSN][3].
-
-    [1]: http://google.com/        "Google"
-    [2]: http://search.yahoo.com/  "Yahoo Search"
-    [3]: http://search.msn.com/    "MSN Search"
-
-Output:
-
-    
    I get 10 times more traffic from Google than from Yahoo or MSN.
    
-
-The title attribute is optional. Link names may contain letters,
-numbers and spaces, but are *not* case sensitive:
-
-    I start my morning with a cup of coffee and
-    [The New York Times][NY Times].
-
-    [ny times]: http://www.nytimes.com/
-
-Output:
-
-    
    I start my morning with a cup of coffee and
-    The New York Times.
    
-
-
-### Images ###
-
-Image syntax is very much like link syntax.
-
-Inline (titles are optional):
-
-    ![alt text](/path/to/img.jpg "Title")
-
-Reference-style:
-
-    ![alt text][id]
-
-    [id]: /path/to/img.jpg "Title"
-
-Both of the above examples produce the same output:
-
-    alt text
-
-
-
-### Code ###
-
-In a regular paragraph, you can create code span by wrapping text in
-backtick quotes. Any ampersands (`&`) and angle brackets (`<` or
-`>`) will automatically be translated into HTML entities. This makes
-it easy to use Markdown to write about HTML example code:
-
-    I strongly recommend against using any `` tags.
-
-    I wish SmartyPants used named entities like `—`
-    instead of decimal-encoded entites like `—`.
-
-Output:
-
-    
    I strongly recommend against using any
-    <blink> tags.
    
-    
-    
    I wish SmartyPants used named entities like
-    &mdash; instead of decimal-encoded
-    entites like &#8212;.
    
-
-
-To specify an entire block of pre-formatted code, indent every line of
-the block by 4 spaces or 1 tab. Just like with code spans, `&`, `<`,
-and `>` characters will be escaped automatically.
-
-Markdown:
-
-    If you want your page to validate under XHTML 1.0 Strict,
-    you've got to put paragraph tags in your blockquotes:
-
-        
    
-            
    For example.
    
-        
    
-
-Output:
-
-    
    If you want your page to validate under XHTML 1.0 Strict,
-    you've got to put paragraph tags in your blockquotes:
    
-    
-    
    <blockquote>
-        <p>For example.</p>
-    </blockquote>
-    
    
diff --git a/oldtests/Original/Markdown_Documentation_Syntax.html b/oldtests/Original/Markdown_Documentation_Syntax.html
deleted file mode 100644
index f379dcf..0000000
--- a/oldtests/Original/Markdown_Documentation_Syntax.html
+++ /dev/null
@@ -1,708 +0,0 @@
-
    Markdown: Syntax
    
-
-
-
    Note: This document is itself written using Markdown; you
-can see the source for it by adding '.text' to the URL.
    
-
    
-
    Overview
    
-
    Philosophy
    
-
    Markdown is intended to be as easy-to-read and easy-to-write as is feasible.
    
-
    Readability, however, is emphasized above all else. A Markdown-formatted
-document should be publishable as-is, as plain text, without looking
-like it's been marked up with tags or formatting instructions. While
-Markdown's syntax has been influenced by several existing text-to-HTML
-filters -- including Setext, atx, Textile, reStructuredText,
-Grutatext, and EtText -- the single biggest source of
-inspiration for Markdown's syntax is the format of plain text email.
    
-
    To this end, Markdown's syntax is comprised entirely of punctuation
-characters, which punctuation characters have been carefully chosen so
-as to look like what they mean. E.g., asterisks around a word actually
-look like *emphasis*. Markdown lists look like, well, lists. Even
-blockquotes look like quoted passages of text, assuming you've ever
-used email.
    
-
    Inline HTML
    
-
    Markdown's syntax is intended for one purpose: to be used as a
-format for writing for the web.
    
-
    Markdown is not a replacement for HTML, or even close to it. Its
-syntax is very small, corresponding only to a very small subset of
-HTML tags. The idea is not to create a syntax that makes it easier
-to insert HTML tags. In my opinion, HTML tags are already easy to
-insert. The idea for Markdown is to make it easy to read, write, and
-edit prose. HTML is a publishing format; Markdown is a writing
-format. Thus, Markdown's formatting syntax only addresses issues that
-can be conveyed in plain text.
    
-
    For any markup that is not covered by Markdown's syntax, you simply
-use HTML itself. There's no need to preface it or delimit it to
-indicate that you're switching from Markdown to HTML; you just use
-the tags.
    
-
    The only restrictions are that block-level HTML elements -- e.g. <div>,
-<table>, <pre>, <p>, etc. -- must be separated from surrounding
-content by blank lines, and the start and end tags of the block should
-not be indented with tabs or spaces. Markdown is smart enough not
-to add extra (unwanted) <p> tags around HTML block-level tags.
    
-
    For example, to add an HTML table to a Markdown article:
    
-
    This is a regular paragraph.
-
-<table>
-    <tr>
-        <td>Foo</td>
-    </tr>
-</table>
-
-This is another regular paragraph.
-
    
-
    Note that Markdown formatting syntax is not processed within block-level
-HTML tags. E.g., you can't use Markdown-style *emphasis* inside an
-HTML block.
    
-
    Span-level HTML tags -- e.g. <span>, <cite>, or <del> -- can be
-used anywhere in a Markdown paragraph, list item, or header. If you
-want, you can even use HTML tags instead of Markdown formatting; e.g. if
-you'd prefer to use HTML <a> or <img> tags instead of Markdown's
-link or image syntax, go right ahead.
    
-
    Unlike block-level HTML tags, Markdown syntax is processed within
-span-level tags.
    
-
    Automatic Escaping for Special Characters
    
-
    In HTML, there are two characters that demand special treatment: <
-and &. Left angle brackets are used to start tags; ampersands are
-used to denote HTML entities. If you want to use them as literal
-characters, you must escape them as entities, e.g. &lt;, and
-&amp;.
    
-
    Ampersands in particular are bedeviling for web writers. If you want to
-write about 'AT&T', you need to write 'AT&amp;T'. You even need to
-escape ampersands within URLs. Thus, if you want to link to:
    
-
    http://images.google.com/images?num=30&q=larry+bird
-
    
-
    you need to encode the URL as:
    
-
    http://images.google.com/images?num=30&amp;q=larry+bird
-
    
-
    in your anchor tag href attribute. Needless to say, this is easy to
-forget, and is probably the single most common source of HTML validation
-errors in otherwise well-marked-up web sites.
    
-
    Markdown allows you to use these characters naturally, taking care of
-all the necessary escaping for you. If you use an ampersand as part of
-an HTML entity, it remains unchanged; otherwise it will be translated
-into &amp;.
    
-
    So, if you want to include a copyright symbol in your article, you can write:
    
-
    &copy;
-
    
-
    and Markdown will leave it alone. But if you write:
    
-
    AT&T
-
    
-
    Markdown will translate it to:
    
-
    AT&amp;T
-
    
-
    Similarly, because Markdown supports inline HTML, if you use
-angle brackets as delimiters for HTML tags, Markdown will treat them as
-such. But if you write:
    
-
    4 < 5
-
    
-
    Markdown will translate it to:
    
-
    4 &lt; 5
-
    
-
    However, inside Markdown code spans and blocks, angle brackets and
-ampersands are always encoded automatically. This makes it easy to use
-Markdown to write about HTML code. (As opposed to raw HTML, which is a
-terrible format for writing about HTML syntax, because every single <
-and & in your example code needs to be escaped.)
    
-
    
-
    Block Elements
    
-
    Paragraphs and Line Breaks
    
-
    A paragraph is simply one or more consecutive lines of text, separated
-by one or more blank lines. (A blank line is any line that looks like a
-blank line -- a line containing nothing but spaces or tabs is considered
-blank.) Normal paragraphs should not be intended with spaces or tabs.
    
-
    The implication of the "one or more consecutive lines of text" rule is
-that Markdown supports "hard-wrapped" text paragraphs. This differs
-significantly from most other text-to-HTML formatters (including Movable
-Type's "Convert Line Breaks" option) which translate every line break
-character in a paragraph into a <br /> tag.
    
-
    When you do want to insert a <br /> break tag using Markdown, you
-end a line with two or more spaces, then type return.
    
-
    Yes, this takes a tad more effort to create a <br />, but a simplistic
-"every line break is a <br />" rule wouldn't work for Markdown.
-Markdown's email-style blockquoting and multi-paragraph list items
-work best -- and look better -- when you format them with hard breaks.
    
-
-
    Markdown supports two styles of headers, Setext and atx.
    
-
    Setext-style headers are "underlined" using equal signs (for first-level
-headers) and dashes (for second-level headers). For example:
    
-
    This is an H1
-=============
-
-This is an H2
--------------
-
    
-
    Any number of underlining ='s or -'s will work.
    
-
    Atx-style headers use 1-6 hash characters at the start of the line,
-corresponding to header levels 1-6. For example:
    
-
    # This is an H1
-
-## This is an H2
-
-###### This is an H6
-
    
-
    Optionally, you may "close" atx-style headers. This is purely
-cosmetic -- you can use this if you think it looks better. The
-closing hashes don't even need to match the number of hashes
-used to open the header. (The number of opening hashes
-determines the header level.) :
    
-
    # This is an H1 #
-
-## This is an H2 ##
-
-### This is an H3 ######
-
    
-
    Blockquotes
    
-
    Markdown uses email-style > characters for blockquoting. If you're
-familiar with quoting passages of text in an email message, then you
-know how to create a blockquote in Markdown. It looks best if you hard
-wrap the text and put a > before every line:
    
-
    > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet,
-> consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus.
-> Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus.
-> 
-> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse
-> id sem consectetuer libero luctus adipiscing.
-
    
-
    Markdown allows you to be lazy and only put the > before the first
-line of a hard-wrapped paragraph:
    
-
    > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet,
-consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus.
-Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus.
-
-> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse
-id sem consectetuer libero luctus adipiscing.
-
    
-
    Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by
-adding additional levels of >:
    
-
    > This is the first level of quoting.
->
-> > This is nested blockquote.
->
-> Back to the first level.
-
    
-
    Blockquotes can contain other Markdown elements, including headers, lists,
-and code blocks:
    
-
    > ## This is a header.
-> 
-> 1.   This is the first list item.
-> 2.   This is the second list item.
-> 
-> Here's some example code:
-> 
->     return shell_exec("echo $input | $markdown_script");
-
    
-
    Any decent text editor should make email-style quoting easy. For
-example, with BBEdit, you can make a selection and choose Increase
-Quote Level from the Text menu.
    
-
    Lists
    
-
    Markdown supports ordered (numbered) and unordered (bulleted) lists.
    
-
    Unordered lists use asterisks, pluses, and hyphens -- interchangably
--- as list markers:
    
-
    *   Red
-*   Green
-*   Blue
-
    
-
    is equivalent to:
    
-
    +   Red
-+   Green
-+   Blue
-
    
-
    and:
    
-
    -   Red
--   Green
--   Blue
-
    
-
    Ordered lists use numbers followed by periods:
    
-
    1.  Bird
-2.  McHale
-3.  Parish
-
    
-
    It's important to note that the actual numbers you use to mark the
-list have no effect on the HTML output Markdown produces. The HTML
-Markdown produces from the above list is:
    
-
    <ol>
-<li>Bird</li>
-<li>McHale</li>
-<li>Parish</li>
-</ol>
-
    
-
    If you instead wrote the list in Markdown like this:
    
-
    1.  Bird
-1.  McHale
-1.  Parish
-
    
-
    or even:
    
-
    3. Bird
-1. McHale
-8. Parish
-
    
-
    you'd get the exact same HTML output. The point is, if you want to,
-you can use ordinal numbers in your ordered Markdown lists, so that
-the numbers in your source match the numbers in your published HTML.
-But if you want to be lazy, you don't have to.
    
-
    If you do use lazy list numbering, however, you should still start the
-list with the number 1. At some point in the future, Markdown may support
-starting ordered lists at an arbitrary number.
    
-
    List markers typically start at the left margin, but may be indented by
-up to three spaces. List markers must be followed by one or more spaces
-or a tab.
    
-
    To make lists look nice, you can wrap items with hanging indents:
    
-
    *   Lorem ipsum dolor sit amet, consectetuer adipiscing elit.
-    Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi,
-    viverra nec, fringilla in, laoreet vitae, risus.
-*   Donec sit amet nisl. Aliquam semper ipsum sit amet velit.
-    Suspendisse id sem consectetuer libero luctus adipiscing.
-
    
-
    But if you want to be lazy, you don't have to:
    
-
    *   Lorem ipsum dolor sit amet, consectetuer adipiscing elit.
-Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi,
-viverra nec, fringilla in, laoreet vitae, risus.
-*   Donec sit amet nisl. Aliquam semper ipsum sit amet velit.
-Suspendisse id sem consectetuer libero luctus adipiscing.
-
    
-
    If list items are separated by blank lines, Markdown will wrap the
-items in <p> tags in the HTML output. For example, this input:
    
-
    *   Bird
-*   Magic
-
    
-
    will turn into:
    
-
    <ul>
-<li>Bird</li>
-<li>Magic</li>
-</ul>
-
    
-
    But this:
    
-
    *   Bird
-
-*   Magic
-
    
-
    will turn into:
    
-
    <ul>
-<li><p>Bird</p></li>
-<li><p>Magic</p></li>
-</ul>
-
    
-
    List items may consist of multiple paragraphs. Each subsequent
-paragraph in a list item must be intended by either 4 spaces
-or one tab:
    
-
    1.  This is a list item with two paragraphs. Lorem ipsum dolor
-    sit amet, consectetuer adipiscing elit. Aliquam hendrerit
-    mi posuere lectus.
-
-    Vestibulum enim wisi, viverra nec, fringilla in, laoreet
-    vitae, risus. Donec sit amet nisl. Aliquam semper ipsum
-    sit amet velit.
-
-2.  Suspendisse id sem consectetuer libero luctus adipiscing.
-
    
-
    It looks nice if you indent every line of the subsequent
-paragraphs, but here again, Markdown will allow you to be
-lazy:
    
-
    *   This is a list item with two paragraphs.
-
-    This is the second paragraph in the list item. You're
-only required to indent the first line. Lorem ipsum dolor
-sit amet, consectetuer adipiscing elit.
-
-*   Another item in the same list.
-
    
-
    To put a blockquote within a list item, the blockquote's >
-delimiters need to be indented:
    
-
    *   A list item with a blockquote:
-
-    > This is a blockquote
-    > inside a list item.
-
    
-
    To put a code block within a list item, the code block needs
-to be indented twice -- 8 spaces or two tabs:
    
-
    *   A list item with a code block:
-
-        <code goes here>
-
    
-
    It's worth noting that it's possible to trigger an ordered list by
-accident, by writing something like this:
    
-
    1986. What a great season.
-
    
-
    In other words, a number-period-space sequence at the beginning of a
-line. To avoid this, you can backslash-escape the period:
    
-
    1986\. What a great season.
-
    
-
    Code Blocks
    
-
    Pre-formatted code blocks are used for writing about programming or
-markup source code. Rather than forming normal paragraphs, the lines
-of a code block are interpreted literally. Markdown wraps a code block
-in both <pre> and <code> tags.
    
-
    To produce a code block in Markdown, simply indent every line of the
-block by at least 4 spaces or 1 tab. For example, given this input:
    
-
    This is a normal paragraph:
-
-    This is a code block.
-
    
-
    Markdown will generate:
    
-
    <p>This is a normal paragraph:</p>
-
-<pre><code>This is a code block.
-</code></pre>
-
    
-
    One level of indentation -- 4 spaces or 1 tab -- is removed from each
-line of the code block. For example, this:
    
-
    Here is an example of AppleScript:
-
-    tell application "Foo"
-        beep
-    end tell
-
    
-
    will turn into:
    
-
    <p>Here is an example of AppleScript:</p>
-
-<pre><code>tell application "Foo"
-    beep
-end tell
-</code></pre>
-
    
-
    A code block continues until it reaches a line that is not indented
-(or the end of the article).
    
-
    Within a code block, ampersands (&) and angle brackets (< and >)
-are automatically converted into HTML entities. This makes it very
-easy to include example HTML source code using Markdown -- just paste
-it and indent it, and Markdown will handle the hassle of encoding the
-ampersands and angle brackets. For example, this:
    
-
        <div class="footer">
-        &copy; 2004 Foo Corporation
-    </div>
-
    
-
    will turn into:
    
-
    <pre><code>&lt;div class="footer"&gt;
-    &amp;copy; 2004 Foo Corporation
-&lt;/div&gt;
-</code></pre>
-
    
-
    Regular Markdown syntax is not processed within code blocks. E.g.,
-asterisks are just literal asterisks within a code block. This means
-it's also easy to use Markdown to write about Markdown's own syntax.
    
-
    Horizontal Rules
    
-
    You can produce a horizontal rule tag (<hr />) by placing three or
-more hyphens, asterisks, or underscores on a line by themselves. If you
-wish, you may use spaces between the hyphens or asterisks. Each of the
-following lines will produce a horizontal rule:
    
-
    * * *
-
-***
-
-*****
-
-- - -
-
----------------------------------------
-
-_ _ _
-
    
-
    
-
    Span Elements
    
-
-
    Markdown supports two style of links: inline and reference.
    
-
    In both styles, the link text is delimited by [square brackets].
    
-
    To create an inline link, use a set of regular parentheses immediately
-after the link text's closing square bracket. Inside the parentheses,
-put the URL where you want the link to point, along with an optional
-title for the link, surrounded in quotes. For example:
    
-
    This is [an example](http://example.com/ "Title") inline link.
-
-[This link](http://example.net/) has no title attribute.
-
    
-
    Will produce:
    
-
    <p>This is <a href="http://example.com/" title="Title">
-an example</a> inline link.</p>
-
-<p><a href="http://example.net/">This link</a> has no
-title attribute.</p>
-
    
-
    If you're referring to a local resource on the same server, you can
-use relative paths:
    
-
    See my [About](/about/) page for details.
-
    
-
    Reference-style links use a second set of square brackets, inside
-which you place a label of your choosing to identify the link:
    
-
    This is [an example][id] reference-style link.
-
    
-
    You can optionally use a space to separate the sets of brackets:
    
-
    This is [an example] [id] reference-style link.
-
    
-
    Then, anywhere in the document, you define your link label like this,
-on a line by itself:
    
-
    [id]: http://example.com/  "Optional Title Here"
-
    
-
    That is:
    
-
      
-
    • Square brackets containing the link identifier (optionally
-indented from the left margin using up to three spaces);
      • 
-
    • followed by a colon;
      • 
-
    • followed by one or more spaces (or tabs);
      • 
-
    • followed by the URL for the link;
      • 
-
    • optionally followed by a title attribute for the link, enclosed
-in double or single quotes.
      • 
-
    
-
    The link URL may, optionally, be surrounded by angle brackets:
    
-
    [id]: <http://example.com/>  "Optional Title Here"
-
    
-
    You can put the title attribute on the next line and use extra spaces
-or tabs for padding, which tends to look better with longer URLs:
    
-
    [id]: http://example.com/longish/path/to/resource/here
-    "Optional Title Here"
-
    
-
    Link definitions are only used for creating links during Markdown
-processing, and are stripped from your document in the HTML output.
    
-
    Link definition names may constist of letters, numbers, spaces, and punctuation -- but they are not case sensitive. E.g. these two links:
    
-
    [link text][a]
-[link text][A]
-
    
-
    are equivalent.
    
-
    The implicit link name shortcut allows you to omit the name of the
-link, in which case the link text itself is used as the name.
-Just use an empty set of square brackets -- e.g., to link the word
-"Google" to the google.com web site, you could simply write:
    
-
    [Google][]
-
    
-
    And then define the link:
    
-
    [Google]: http://google.com/
-
    
-
    Because link names may contain spaces, this shortcut even works for
-multiple words in the link text:
    
-
    Visit [Daring Fireball][] for more information.
-
    
-
    And then define the link:
    
-
    [Daring Fireball]: http://daringfireball.net/
-
    
-
    Link definitions can be placed anywhere in your Markdown document. I
-tend to put them immediately after each paragraph in which they're
-used, but if you want, you can put them all at the end of your
-document, sort of like footnotes.
    
-
    Here's an example of reference links in action:
    
-
    I get 10 times more traffic from [Google] [1] than from
-[Yahoo] [2] or [MSN] [3].
-
-  [1]: http://google.com/        "Google"
-  [2]: http://search.yahoo.com/  "Yahoo Search"
-  [3]: http://search.msn.com/    "MSN Search"
-
    
-
    Using the implicit link name shortcut, you could instead write:
    
-
    I get 10 times more traffic from [Google][] than from
-[Yahoo][] or [MSN][].
-
-  [google]: http://google.com/        "Google"
-  [yahoo]:  http://search.yahoo.com/  "Yahoo Search"
-  [msn]:    http://search.msn.com/    "MSN Search"
-
    
-
    Both of the above examples will produce the following HTML output:
    
-
    <p>I get 10 times more traffic from <a href="http://google.com/"
-title="Google">Google</a> than from
-<a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a>
-or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p>
-
    
-
    For comparison, here is the same paragraph written using
-Markdown's inline link style:
    
-
    I get 10 times more traffic from [Google](http://google.com/ "Google")
-than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or
-[MSN](http://search.msn.com/ "MSN Search").
-
    
-
    The point of reference-style links is not that they're easier to
-write. The point is that with reference-style links, your document
-source is vastly more readable. Compare the above examples: using
-reference-style links, the paragraph itself is only 81 characters
-long; with inline-style links, it's 176 characters; and as raw HTML,
-it's 234 characters. In the raw HTML, there's more markup than there
-is text.
    
-
    With Markdown's reference-style links, a source document much more
-closely resembles the final output, as rendered in a browser. By
-allowing you to move the markup-related metadata out of the paragraph,
-you can add links without interrupting the narrative flow of your
-prose.
    
-
    Emphasis
    
-
    Markdown treats asterisks (*) and underscores (_) as indicators of
-emphasis. Text wrapped with one * or _ will be wrapped with an
-HTML <em> tag; double *'s or _'s will be wrapped with an HTML
-<strong> tag. E.g., this input:
    
-
    *single asterisks*
-
-_single underscores_
-
-**double asterisks**
-
-__double underscores__
-
    
-
    will produce:
    
-
    <em>single asterisks</em>
-
-<em>single underscores</em>
-
-<strong>double asterisks</strong>
-
-<strong>double underscores</strong>
-
    
-
    You can use whichever style you prefer; the lone restriction is that
-the same character must be used to open and close an emphasis span.
    
-
    Emphasis can be used in the middle of a word:
    
-
    un*fucking*believable
-
    
-
    But if you surround an * or _ with spaces, it'll be treated as a
-literal asterisk or underscore.
    
-
    To produce a literal asterisk or underscore at a position where it
-would otherwise be used as an emphasis delimiter, you can backslash
-escape it:
    
-
    \*this text is surrounded by literal asterisks\*
-
    
-
    Code
    
-
    To indicate a span of code, wrap it with backtick quotes (`).
-Unlike a pre-formatted code block, a code span indicates code within a
-normal paragraph. For example:
    
-
    Use the `printf()` function.
-
    
-
    will produce:
    
-
    <p>Use the <code>printf()</code> function.</p>
-
    
-
    To include a literal backtick character within a code span, you can use
-multiple backticks as the opening and closing delimiters:
    
-
    ``There is a literal backtick (`) here.``
-
    
-
    which will produce this:
    
-
    <p><code>There is a literal backtick (`) here.</code></p>
-
    
-
    The backtick delimiters surrounding a code span may include spaces --
-one after the opening, one before the closing. This allows you to place
-literal backtick characters at the beginning or end of a code span:
    
-
    A single backtick in a code span: `` ` ``
-
-A backtick-delimited string in a code span: `` `foo` ``
-
    
-
    will produce:
    
-
    <p>A single backtick in a code span: <code>`</code></p>
-
-<p>A backtick-delimited string in a code span: <code>`foo`</code></p>
-
    
-
    With a code span, ampersands and angle brackets are encoded as HTML
-entities automatically, which makes it easy to include example HTML
-tags. Markdown will turn this:
    
-
    Please don't use any `<blink>` tags.
-
    
-
    into:
    
-
    <p>Please don't use any <code>&lt;blink&gt;</code> tags.</p>
-
    
-
    You can write this:
    
-
    `&#8212;` is the decimal-encoded equivalent of `&mdash;`.
-
    
-
    to produce:
    
-
    <p><code>&amp;#8212;</code> is the decimal-encoded
-equivalent of <code>&amp;mdash;</code>.</p>
-
    
-
    Images
    
-
    Admittedly, it's fairly difficult to devise a "natural" syntax for
-placing images into a plain text document format.
    
-
    Markdown uses an image syntax that is intended to resemble the syntax
-for links, allowing for two styles: inline and reference.
    
-
    Inline image syntax looks like this:
    
-
    ![Alt text](/path/to/img.jpg)
-
-![Alt text](/path/to/img.jpg "Optional title")
-
    
-
    That is:
    
-
      
-
    • An exclamation mark: !;
      • 
-
    • followed by a set of square brackets, containing the alt
-attribute text for the image;
      • 
-
    • followed by a set of parentheses, containing the URL or path to
-the image, and an optional title attribute enclosed in double
-or single quotes.
      • 
-
    
-
    Reference-style image syntax looks like this:
    
-
    ![Alt text][id]
-
    
-
    Where "id" is the name of a defined image reference. Image references
-are defined using syntax identical to link references:
    
-
    [id]: url/to/image  "Optional title attribute"
-
    
-
    As of this writing, Markdown has no syntax for specifying the
-dimensions of an image; if this is important to you, you can simply
-use regular HTML <img> tags.
    
-
    
-
    Miscellaneous
    
-
-
    Markdown supports a shortcut style for creating "automatic" links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link, you can do this:
    
-
    <http://example.com/>
-
    
-
    Markdown will turn this into:
    
-
    <a href="http://example.com/">http://example.com/</a>
-
    
-
    Automatic links for email addresses work similarly, except that
-Markdown will also perform a bit of randomized decimal and hex
-entity-encoding to help obscure your address from address-harvesting
-spambots. For example, Markdown will turn this:
    
-
    <address@example.com>
-
    
-
    into something like this:
    
-
    <a href="&#x6D;&#x61;i&#x6C;&#x74;&#x6F;:&#x61;&#x64;&#x64;&#x72;&#x65;
-&#115;&#115;&#64;&#101;&#120;&#x61;&#109;&#x70;&#x6C;e&#x2E;&#99;&#111;
-&#109;">&#x61;&#x64;&#x64;&#x72;&#x65;&#115;&#115;&#64;&#101;&#120;&#x61;
-&#109;&#x70;&#x6C;e&#x2E;&#99;&#111;&#109;</a>
-
    
-
    which will render in a browser as a clickable link to "address@example.com".
    
-
    (This sort of entity-encoding trick will indeed fool many, if not
-most, address-harvesting bots, but it definitely won't fool all of
-them. It's better than nothing, but an address published in this way
-will probably eventually start receiving spam.)
    
-
    Backslash Escapes
    
-
    Markdown allows you to use backslash escapes to generate literal
-characters which would otherwise have special meaning in Markdown's
-formatting syntax. For example, if you wanted to surround a word with
-literal asterisks (instead of an HTML <em> tag), you can backslashes
-before the asterisks, like this:
    
-
    \*literal asterisks\*
-
    
-
    Markdown provides backslash escapes for the following characters:
    
-
    \   backslash
-`   backtick
-*   asterisk
-_   underscore
-{}  curly braces
-[]  square brackets
-()  parentheses
-#   hash mark
-+   plus sign
--   minus sign (hyphen)
-.   dot
-!   exclamation mark
-
    
diff --git a/oldtests/Original/Markdown_Documentation_Syntax.markdown b/oldtests/Original/Markdown_Documentation_Syntax.markdown
deleted file mode 100644
index 57360a1..0000000
--- a/oldtests/Original/Markdown_Documentation_Syntax.markdown
+++ /dev/null
@@ -1,888 +0,0 @@
-Markdown: Syntax
-================
-
-
-
-
-*   [Overview](#overview)
-    *   [Philosophy](#philosophy)
-    *   [Inline HTML](#html)
-    *   [Automatic Escaping for Special Characters](#autoescape)
-*   [Block Elements](#block)
-    *   [Paragraphs and Line Breaks](#p)
-    *   [Headers](#header)
-    *   [Blockquotes](#blockquote)
-    *   [Lists](#list)
-    *   [Code Blocks](#precode)
-    *   [Horizontal Rules](#hr)
-*   [Span Elements](#span)
-    *   [Links](#link)
-    *   [Emphasis](#em)
-    *   [Code](#code)
-    *   [Images](#img)
-*   [Miscellaneous](#misc)
-    *   [Backslash Escapes](#backslash)
-    *   [Automatic Links](#autolink)
-
-
-**Note:** This document is itself written using Markdown; you
-can [see the source for it by adding '.text' to the URL][src].
-
-  [src]: /projects/markdown/syntax.text
-
-* * *
-
-
    Overview
    
-
-
    Philosophy
    
-
-Markdown is intended to be as easy-to-read and easy-to-write as is feasible.
-
-Readability, however, is emphasized above all else. A Markdown-formatted
-document should be publishable as-is, as plain text, without looking
-like it's been marked up with tags or formatting instructions. While
-Markdown's syntax has been influenced by several existing text-to-HTML
-filters -- including [Setext] [1], [atx] [2], [Textile] [3], [reStructuredText] [4],
-[Grutatext] [5], and [EtText] [6] -- the single biggest source of
-inspiration for Markdown's syntax is the format of plain text email.
-
-  [1]: http://docutils.sourceforge.net/mirror/setext.html
-  [2]: http://www.aaronsw.com/2002/atx/
-  [3]: http://textism.com/tools/textile/
-  [4]: http://docutils.sourceforge.net/rst.html
-  [5]: http://www.triptico.com/software/grutatxt.html
-  [6]: http://ettext.taint.org/doc/
-
-To this end, Markdown's syntax is comprised entirely of punctuation
-characters, which punctuation characters have been carefully chosen so
-as to look like what they mean. E.g., asterisks around a word actually
-look like \*emphasis\*. Markdown lists look like, well, lists. Even
-blockquotes look like quoted passages of text, assuming you've ever
-used email.
-
-
-
-
    Inline HTML
    
-
-Markdown's syntax is intended for one purpose: to be used as a
-format for *writing* for the web.
-
-Markdown is not a replacement for HTML, or even close to it. Its
-syntax is very small, corresponding only to a very small subset of
-HTML tags. The idea is *not* to create a syntax that makes it easier
-to insert HTML tags. In my opinion, HTML tags are already easy to
-insert. The idea for Markdown is to make it easy to read, write, and
-edit prose. HTML is a *publishing* format; Markdown is a *writing*
-format. Thus, Markdown's formatting syntax only addresses issues that
-can be conveyed in plain text.
-
-For any markup that is not covered by Markdown's syntax, you simply
-use HTML itself. There's no need to preface it or delimit it to
-indicate that you're switching from Markdown to HTML; you just use
-the tags.
-
-The only restrictions are that block-level HTML elements -- e.g. `
    `,
-``, `
    `, `
    `, etc. -- must be separated from surrounding
-content by blank lines, and the start and end tags of the block should
-not be indented with tabs or spaces. Markdown is smart enough not
-to add extra (unwanted) `
    ` tags around HTML block-level tags.
-
-For example, to add an HTML table to a Markdown article:
-
-    This is a regular paragraph.
-
-    
    
-        
-            
-        
-    
    Foo
    
-
-    This is another regular paragraph.
-
-Note that Markdown formatting syntax is not processed within block-level
-HTML tags. E.g., you can't use Markdown-style `*emphasis*` inside an
-HTML block.
-
-Span-level HTML tags -- e.g. ``, ``, or `` -- can be
-used anywhere in a Markdown paragraph, list item, or header. If you
-want, you can even use HTML tags instead of Markdown formatting; e.g. if
-you'd prefer to use HTML `` or `` tags instead of Markdown's
-link or image syntax, go right ahead.
-
-Unlike block-level HTML tags, Markdown syntax *is* processed within
-span-level tags.
-
-
-
    Automatic Escaping for Special Characters
    
-
-In HTML, there are two characters that demand special treatment: `<`
-and `&`. Left angle brackets are used to start tags; ampersands are
-used to denote HTML entities. If you want to use them as literal
-characters, you must escape them as entities, e.g. `<`, and
-`&`.
-
-Ampersands in particular are bedeviling for web writers. If you want to
-write about 'AT&T', you need to write '`AT&T`'. You even need to
-escape ampersands within URLs. Thus, if you want to link to:
-
-    http://images.google.com/images?num=30&q=larry+bird
-
-you need to encode the URL as:
-
-    http://images.google.com/images?num=30&q=larry+bird
-
-in your anchor tag `href` attribute. Needless to say, this is easy to
-forget, and is probably the single most common source of HTML validation
-errors in otherwise well-marked-up web sites.
-
-Markdown allows you to use these characters naturally, taking care of
-all the necessary escaping for you. If you use an ampersand as part of
-an HTML entity, it remains unchanged; otherwise it will be translated
-into `&`.
-
-So, if you want to include a copyright symbol in your article, you can write:
-
-    ©
-
-and Markdown will leave it alone. But if you write:
-
-    AT&T
-
-Markdown will translate it to:
-
-    AT&T
-
-Similarly, because Markdown supports [inline HTML](#html), if you use
-angle brackets as delimiters for HTML tags, Markdown will treat them as
-such. But if you write:
-
-    4 < 5
-
-Markdown will translate it to:
-
-    4 < 5
-
-However, inside Markdown code spans and blocks, angle brackets and
-ampersands are *always* encoded automatically. This makes it easy to use
-Markdown to write about HTML code. (As opposed to raw HTML, which is a
-terrible format for writing about HTML syntax, because every single `<`
-and `&` in your example code needs to be escaped.)
-
-
-* * *
-
-
-
    Block Elements
    
-
-
-
    Paragraphs and Line Breaks
    
-
-A paragraph is simply one or more consecutive lines of text, separated
-by one or more blank lines. (A blank line is any line that looks like a
-blank line -- a line containing nothing but spaces or tabs is considered
-blank.) Normal paragraphs should not be intended with spaces or tabs.
-
-The implication of the "one or more consecutive lines of text" rule is
-that Markdown supports "hard-wrapped" text paragraphs. This differs
-significantly from most other text-to-HTML formatters (including Movable
-Type's "Convert Line Breaks" option) which translate every line break
-character in a paragraph into a `
    ` tag.
-
-When you *do* want to insert a `
    ` break tag using Markdown, you
-end a line with two or more spaces, then type return.
-
-Yes, this takes a tad more effort to create a `
    `, but a simplistic
-"every line break is a `
    `" rule wouldn't work for Markdown.
-Markdown's email-style [blockquoting][bq] and multi-paragraph [list items][l]
-work best -- and look better -- when you format them with hard breaks.
-
-  [bq]: #blockquote
-  [l]:  #list
-
-
-
-
-
-Markdown supports two styles of headers, [Setext] [1] and [atx] [2].
-
-Setext-style headers are "underlined" using equal signs (for first-level
-headers) and dashes (for second-level headers). For example:
-
-    This is an H1
-    =============
-
-    This is an H2
-    -------------
-
-Any number of underlining `=`'s or `-`'s will work.
-
-Atx-style headers use 1-6 hash characters at the start of the line,
-corresponding to header levels 1-6. For example:
-
-    # This is an H1
-
-    ## This is an H2
-
-    ###### This is an H6
-
-Optionally, you may "close" atx-style headers. This is purely
-cosmetic -- you can use this if you think it looks better. The
-closing hashes don't even need to match the number of hashes
-used to open the header. (The number of opening hashes
-determines the header level.) :
-
-    # This is an H1 #
-
-    ## This is an H2 ##
-
-    ### This is an H3 ######
-
-
-
    Blockquotes
    
-
-Markdown uses email-style `>` characters for blockquoting. If you're
-familiar with quoting passages of text in an email message, then you
-know how to create a blockquote in Markdown. It looks best if you hard
-wrap the text and put a `>` before every line:
-
-    > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet,
-    > consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus.
-    > Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus.
-    > 
-    > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse
-    > id sem consectetuer libero luctus adipiscing.
-
-Markdown allows you to be lazy and only put the `>` before the first
-line of a hard-wrapped paragraph:
-
-    > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet,
-    consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus.
-    Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus.
-
-    > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse
-    id sem consectetuer libero luctus adipiscing.
-
-Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by
-adding additional levels of `>`:
-
-    > This is the first level of quoting.
-    >
-    > > This is nested blockquote.
-    >
-    > Back to the first level.
-
-Blockquotes can contain other Markdown elements, including headers, lists,
-and code blocks:
-
-	> ## This is a header.
-	> 
-	> 1.   This is the first list item.
-	> 2.   This is the second list item.
-	> 
-	> Here's some example code:
-	> 
-	>     return shell_exec("echo $input | $markdown_script");
-
-Any decent text editor should make email-style quoting easy. For
-example, with BBEdit, you can make a selection and choose Increase
-Quote Level from the Text menu.
-
-
-
    Lists
    
-
-Markdown supports ordered (numbered) and unordered (bulleted) lists.
-
-Unordered lists use asterisks, pluses, and hyphens -- interchangably
--- as list markers:
-
-    *   Red
-    *   Green
-    *   Blue
-
-is equivalent to:
-
-    +   Red
-    +   Green
-    +   Blue
-
-and:
-
-    -   Red
-    -   Green
-    -   Blue
-
-Ordered lists use numbers followed by periods:
-
-    1.  Bird
-    2.  McHale
-    3.  Parish
-
-It's important to note that the actual numbers you use to mark the
-list have no effect on the HTML output Markdown produces. The HTML
-Markdown produces from the above list is:
-
-    
      
-    
    1. Bird
      2. 
-    
    2. McHale
      3. 
-    
    3. Parish
      4. 
-    
    
-
-If you instead wrote the list in Markdown like this:
-
-    1.  Bird
-    1.  McHale
-    1.  Parish
-
-or even:
-
-    3. Bird
-    1. McHale
-    8. Parish
-
-you'd get the exact same HTML output. The point is, if you want to,
-you can use ordinal numbers in your ordered Markdown lists, so that
-the numbers in your source match the numbers in your published HTML.
-But if you want to be lazy, you don't have to.
-
-If you do use lazy list numbering, however, you should still start the
-list with the number 1. At some point in the future, Markdown may support
-starting ordered lists at an arbitrary number.
-
-List markers typically start at the left margin, but may be indented by
-up to three spaces. List markers must be followed by one or more spaces
-or a tab.
-
-To make lists look nice, you can wrap items with hanging indents:
-
-    *   Lorem ipsum dolor sit amet, consectetuer adipiscing elit.
-        Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi,
-        viverra nec, fringilla in, laoreet vitae, risus.
-    *   Donec sit amet nisl. Aliquam semper ipsum sit amet velit.
-        Suspendisse id sem consectetuer libero luctus adipiscing.
-
-But if you want to be lazy, you don't have to:
-
-    *   Lorem ipsum dolor sit amet, consectetuer adipiscing elit.
-    Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi,
-    viverra nec, fringilla in, laoreet vitae, risus.
-    *   Donec sit amet nisl. Aliquam semper ipsum sit amet velit.
-    Suspendisse id sem consectetuer libero luctus adipiscing.
-
-If list items are separated by blank lines, Markdown will wrap the
-items in `
    ` tags in the HTML output. For example, this input:
-
-    *   Bird
-    *   Magic
-
-will turn into:
-
-    
      
-    
    • Bird
      • 
-    
    • Magic
      • 
-    
    
-
-But this:
-
-    *   Bird
-
-    *   Magic
-
-will turn into:
-
-    
      
-    
    • Bird
      • 
-    
    • Magic
      • 
-    
    
-
-List items may consist of multiple paragraphs. Each subsequent
-paragraph in a list item must be intended by either 4 spaces
-or one tab:
-
-    1.  This is a list item with two paragraphs. Lorem ipsum dolor
-        sit amet, consectetuer adipiscing elit. Aliquam hendrerit
-        mi posuere lectus.
-
-        Vestibulum enim wisi, viverra nec, fringilla in, laoreet
-        vitae, risus. Donec sit amet nisl. Aliquam semper ipsum
-        sit amet velit.
-
-    2.  Suspendisse id sem consectetuer libero luctus adipiscing.
-
-It looks nice if you indent every line of the subsequent
-paragraphs, but here again, Markdown will allow you to be
-lazy:
-
-    *   This is a list item with two paragraphs.
-
-        This is the second paragraph in the list item. You're
-    only required to indent the first line. Lorem ipsum dolor
-    sit amet, consectetuer adipiscing elit.
-
-    *   Another item in the same list.
-
-To put a blockquote within a list item, the blockquote's `>`
-delimiters need to be indented:
-
-    *   A list item with a blockquote:
-
-        > This is a blockquote
-        > inside a list item.
-
-To put a code block within a list item, the code block needs
-to be indented *twice* -- 8 spaces or two tabs:
-
-    *   A list item with a code block:
-
-            
-
-
-It's worth noting that it's possible to trigger an ordered list by
-accident, by writing something like this:
-
-    1986. What a great season.
-
-In other words, a *number-period-space* sequence at the beginning of a
-line. To avoid this, you can backslash-escape the period:
-
-    1986\. What a great season.
-
-
-
-
    Code Blocks
    
-
-Pre-formatted code blocks are used for writing about programming or
-markup source code. Rather than forming normal paragraphs, the lines
-of a code block are interpreted literally. Markdown wraps a code block
-in both `
    ` and `` tags.
-
-To produce a code block in Markdown, simply indent every line of the
-block by at least 4 spaces or 1 tab. For example, given this input:
-
-    This is a normal paragraph:
-
-        This is a code block.
-
-Markdown will generate:
-
-    
    This is a normal paragraph:
    
-
-    
    This is a code block.
-    
    
-
-One level of indentation -- 4 spaces or 1 tab -- is removed from each
-line of the code block. For example, this:
-
-    Here is an example of AppleScript:
-
-        tell application "Foo"
-            beep
-        end tell
-
-will turn into:
-
-    
    Here is an example of AppleScript:
    
-
-    
    tell application "Foo"
-        beep
-    end tell
-    
    
-
-A code block continues until it reaches a line that is not indented
-(or the end of the article).
-
-Within a code block, ampersands (`&`) and angle brackets (`<` and `>`)
-are automatically converted into HTML entities. This makes it very
-easy to include example HTML source code using Markdown -- just paste
-it and indent it, and Markdown will handle the hassle of encoding the
-ampersands and angle brackets. For example, this:
-
-        
    
-            © 2004 Foo Corporation
-        
    
-
-will turn into:
-
-    
    <div class="footer">
-        &copy; 2004 Foo Corporation
-    </div>
-    
    
-
-Regular Markdown syntax is not processed within code blocks. E.g.,
-asterisks are just literal asterisks within a code block. This means
-it's also easy to use Markdown to write about Markdown's own syntax.
-
-
-
-
    Horizontal Rules
    
-
-You can produce a horizontal rule tag (`
    `) by placing three or
-more hyphens, asterisks, or underscores on a line by themselves. If you
-wish, you may use spaces between the hyphens or asterisks. Each of the
-following lines will produce a horizontal rule:
-
-    * * *
-
-    ***
-
-    *****
-	
-    - - -
-
-    ---------------------------------------
-
-	_ _ _
-
-
-* * *
-
-
    Span Elements
    
-
-
-
-Markdown supports two style of links: *inline* and *reference*.
-
-In both styles, the link text is delimited by [square brackets].
-
-To create an inline link, use a set of regular parentheses immediately
-after the link text's closing square bracket. Inside the parentheses,
-put the URL where you want the link to point, along with an *optional*
-title for the link, surrounded in quotes. For example:
-
-    This is [an example](http://example.com/ "Title") inline link.
-
-    [This link](http://example.net/) has no title attribute.
-
-Will produce:
-
-    
    This is 
-    an example inline link.
    
-
-    
    This link has no
-    title attribute.
    
-
-If you're referring to a local resource on the same server, you can
-use relative paths:
-
-    See my [About](/about/) page for details.
-
-Reference-style links use a second set of square brackets, inside
-which you place a label of your choosing to identify the link:
-
-    This is [an example][id] reference-style link.
-
-You can optionally use a space to separate the sets of brackets:
-
-    This is [an example] [id] reference-style link.
-
-Then, anywhere in the document, you define your link label like this,
-on a line by itself:
-
-    [id]: http://example.com/  "Optional Title Here"
-
-That is:
-
-*   Square brackets containing the link identifier (optionally
-    indented from the left margin using up to three spaces);
-*   followed by a colon;
-*   followed by one or more spaces (or tabs);
-*   followed by the URL for the link;
-*   optionally followed by a title attribute for the link, enclosed
-    in double or single quotes.
-
-The link URL may, optionally, be surrounded by angle brackets:
-
-    [id]:   "Optional Title Here"
-
-You can put the title attribute on the next line and use extra spaces
-or tabs for padding, which tends to look better with longer URLs:
-
-    [id]: http://example.com/longish/path/to/resource/here
-        "Optional Title Here"
-
-Link definitions are only used for creating links during Markdown
-processing, and are stripped from your document in the HTML output.
-
-Link definition names may constist of letters, numbers, spaces, and punctuation -- but they are *not* case sensitive. E.g. these two links:
-
-	[link text][a]
-	[link text][A]
-
-are equivalent.
-
-The *implicit link name* shortcut allows you to omit the name of the
-link, in which case the link text itself is used as the name.
-Just use an empty set of square brackets -- e.g., to link the word
-"Google" to the google.com web site, you could simply write:
-
-	[Google][]
-
-And then define the link:
-
-	[Google]: http://google.com/
-
-Because link names may contain spaces, this shortcut even works for
-multiple words in the link text:
-
-	Visit [Daring Fireball][] for more information.
-
-And then define the link:
-	
-	[Daring Fireball]: http://daringfireball.net/
-
-Link definitions can be placed anywhere in your Markdown document. I
-tend to put them immediately after each paragraph in which they're
-used, but if you want, you can put them all at the end of your
-document, sort of like footnotes.
-
-Here's an example of reference links in action:
-
-    I get 10 times more traffic from [Google] [1] than from
-    [Yahoo] [2] or [MSN] [3].
-
-      [1]: http://google.com/        "Google"
-      [2]: http://search.yahoo.com/  "Yahoo Search"
-      [3]: http://search.msn.com/    "MSN Search"
-
-Using the implicit link name shortcut, you could instead write:
-
-    I get 10 times more traffic from [Google][] than from
-    [Yahoo][] or [MSN][].
-
-      [google]: http://google.com/        "Google"
-      [yahoo]:  http://search.yahoo.com/  "Yahoo Search"
-      [msn]:    http://search.msn.com/    "MSN Search"
-
-Both of the above examples will produce the following HTML output:
-
-    
    I get 10 times more traffic from Google than from
-    Yahoo
-    or MSN.
    
-
-For comparison, here is the same paragraph written using
-Markdown's inline link style:
-
-    I get 10 times more traffic from [Google](http://google.com/ "Google")
-    than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or
-    [MSN](http://search.msn.com/ "MSN Search").
-
-The point of reference-style links is not that they're easier to
-write. The point is that with reference-style links, your document
-source is vastly more readable. Compare the above examples: using
-reference-style links, the paragraph itself is only 81 characters
-long; with inline-style links, it's 176 characters; and as raw HTML,
-it's 234 characters. In the raw HTML, there's more markup than there
-is text.
-
-With Markdown's reference-style links, a source document much more
-closely resembles the final output, as rendered in a browser. By
-allowing you to move the markup-related metadata out of the paragraph,
-you can add links without interrupting the narrative flow of your
-prose.
-
-
-
    Emphasis
    
-
-Markdown treats asterisks (`*`) and underscores (`_`) as indicators of
-emphasis. Text wrapped with one `*` or `_` will be wrapped with an
-HTML `` tag; double `*`'s or `_`'s will be wrapped with an HTML
-`` tag. E.g., this input:
-
-    *single asterisks*
-
-    _single underscores_
-
-    **double asterisks**
-
-    __double underscores__
-
-will produce:
-
-    single asterisks
-
-    single underscores
-
-    double asterisks
-
-    double underscores
-
-You can use whichever style you prefer; the lone restriction is that
-the same character must be used to open and close an emphasis span.
-
-Emphasis can be used in the middle of a word:
-
-    un*fucking*believable
-
-But if you surround an `*` or `_` with spaces, it'll be treated as a
-literal asterisk or underscore.
-
-To produce a literal asterisk or underscore at a position where it
-would otherwise be used as an emphasis delimiter, you can backslash
-escape it:
-
-    \*this text is surrounded by literal asterisks\*
-
-
-
-
    Code
    
-
-To indicate a span of code, wrap it with backtick quotes (`` ` ``).
-Unlike a pre-formatted code block, a code span indicates code within a
-normal paragraph. For example:
-
-    Use the `printf()` function.
-
-will produce:
-
-    
    Use the printf() function.
    
-
-To include a literal backtick character within a code span, you can use
-multiple backticks as the opening and closing delimiters:
-
-    ``There is a literal backtick (`) here.``
-
-which will produce this:
-
-    
    There is a literal backtick (`) here.
    
-
-The backtick delimiters surrounding a code span may include spaces --
-one after the opening, one before the closing. This allows you to place
-literal backtick characters at the beginning or end of a code span:
-
-	A single backtick in a code span: `` ` ``
-	
-	A backtick-delimited string in a code span: `` `foo` ``
-
-will produce:
-
-	
    A single backtick in a code span: `
    
-	
-	
    A backtick-delimited string in a code span: `foo`
    
-
-With a code span, ampersands and angle brackets are encoded as HTML
-entities automatically, which makes it easy to include example HTML
-tags. Markdown will turn this:
-
-    Please don't use any `` tags.
-
-into:
-
-    
    Please don't use any <blink> tags.
    
-
-You can write this:
-
-    `—` is the decimal-encoded equivalent of `—`.
-
-to produce:
-
-    
    &#8212; is the decimal-encoded
-    equivalent of &mdash;.
    
-
-
-
-
    Images
    
-
-Admittedly, it's fairly difficult to devise a "natural" syntax for
-placing images into a plain text document format.
-
-Markdown uses an image syntax that is intended to resemble the syntax
-for links, allowing for two styles: *inline* and *reference*.
-
-Inline image syntax looks like this:
-
-    ![Alt text](/path/to/img.jpg)
-
-    ![Alt text](/path/to/img.jpg "Optional title")
-
-That is:
-
-*   An exclamation mark: `!`;
-*   followed by a set of square brackets, containing the `alt`
-    attribute text for the image;
-*   followed by a set of parentheses, containing the URL or path to
-    the image, and an optional `title` attribute enclosed in double
-    or single quotes.
-
-Reference-style image syntax looks like this:
-
-    ![Alt text][id]
-
-Where "id" is the name of a defined image reference. Image references
-are defined using syntax identical to link references:
-
-    [id]: url/to/image  "Optional title attribute"
-
-As of this writing, Markdown has no syntax for specifying the
-dimensions of an image; if this is important to you, you can simply
-use regular HTML `` tags.
-
-
-* * *
-
-
-
    Miscellaneous
    
-
-
-
-Markdown supports a shortcut style for creating "automatic" links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link, you can do this:
-
-    
-    
-Markdown will turn this into:
-
-    http://example.com/
-
-Automatic links for email addresses work similarly, except that
-Markdown will also perform a bit of randomized decimal and hex
-entity-encoding to help obscure your address from address-harvesting
-spambots. For example, Markdown will turn this:
-
-    
-
-into something like this:
-
-    address@exa
-    mple.com
-
-which will render in a browser as a clickable link to "address@example.com".
-
-(This sort of entity-encoding trick will indeed fool many, if not
-most, address-harvesting bots, but it definitely won't fool all of
-them. It's better than nothing, but an address published in this way
-will probably eventually start receiving spam.)
-
-
-
-
    Backslash Escapes
    
-
-Markdown allows you to use backslash escapes to generate literal
-characters which would otherwise have special meaning in Markdown's
-formatting syntax. For example, if you wanted to surround a word with
-literal asterisks (instead of an HTML `` tag), you can backslashes
-before the asterisks, like this:
-
-    \*literal asterisks\*
-
-Markdown provides backslash escapes for the following characters:
-
-    \   backslash
-    `   backtick
-    *   asterisk
-    _   underscore
-    {}  curly braces
-    []  square brackets
-    ()  parentheses
-    #   hash mark
-	+	plus sign
-	-	minus sign (hyphen)
-    .   dot
-    !   exclamation mark
-
diff --git a/oldtests/Original/Nested_blockquotes.html b/oldtests/Original/Nested_blockquotes.html
deleted file mode 100644
index 02efc59..0000000
--- a/oldtests/Original/Nested_blockquotes.html
+++ /dev/null
@@ -1,7 +0,0 @@
-
    
-
    foo
    
-
    
-
    bar
    
-
    
-
    foo
    
-
    
diff --git a/oldtests/Original/Nested_blockquotes.markdown b/oldtests/Original/Nested_blockquotes.markdown
deleted file mode 100644
index ed3c624..0000000
--- a/oldtests/Original/Nested_blockquotes.markdown
+++ /dev/null
@@ -1,5 +0,0 @@
-> foo
->
-> > bar
->
-> foo
diff --git a/oldtests/Original/Ordered_and_unordered_lists.html b/oldtests/Original/Ordered_and_unordered_lists.html
deleted file mode 100644
index 78d752e..0000000
--- a/oldtests/Original/Ordered_and_unordered_lists.html
+++ /dev/null
@@ -1,112 +0,0 @@
-
    Unordered
    
-
    Asterisks tight:
    
-
      
-
    • asterisk 1
      • 
-
    • asterisk 2
      • 
-
    • asterisk 3
      • 
-
    
-
    Asterisks loose:
    
-
      
-
    • asterisk 1
      • 
-
    • asterisk 2
      • 
-
    • asterisk 3
      • 
-
    
-
    
-
    Pluses tight:
    
-
      
-
    • Plus 1
      • 
-
    • Plus 2
      • 
-
    • Plus 3
      • 
-
    
-
    Pluses loose:
    
-
      
-
    • Plus 1
      • 
-
    • Plus 2
      • 
-
    • Plus 3
      • 
-
    
-
    
-
    Minuses tight:
    
-
      
-
    • Minus 1
      • 
-
    • Minus 2
      • 
-
    • Minus 3
      • 
-
    
-
    Minuses loose:
    
-
      
-
    • Minus 1
      • 
-
    • Minus 2
      • 
-
    • Minus 3
      • 
-
    
-
    Ordered
    
-
    Tight:
    
-
      
-
    1. First
      2. 
-
    2. Second
      3. 
-
    3. Third
      4. 
-
    
-
    and:
    
-
      
-
    1. One
      2. 
-
    2. Two
      3. 
-
    3. Three
      4. 
-
    
-
    Loose using tabs:
    
-
      
-
    1. First
      2. 
-
    2. Second
      3. 
-
    3. Third
      4. 
-
    
-
    and using spaces:
    
-
      
-
    1. One
      2. 
-
    2. Two
      3. 
-
    3. Three
      4. 
-
    
-
    Multiple paragraphs:
    
-
      
-
    1. Item 1, graf one.
      
-
      Item 2. graf two. The quick brown fox jumped over the lazy dog's
-back.
      2. 
-
    2. Item 2.
      3. 
-
    3. Item 3.
      4. 
-
    
-
    Nested
    
-
      
-
    • Tab
-
        
-
      • Tab
-
          
-
        • Tab
          • 
-
        • 
-
      • 
-
    
-
    Here's another:
    
-
      
-
    1. First
      2. 
-
    2. Second:
-
        
-
      • Fee
        • 
-
      • Fie
        • 
-
      • Foe
        • 
-
      3. 
-
    3. Third
      4. 
-
    
-
    Same thing but with paragraphs:
    
-
      
-
    1. First
      2. 
-
    2. Second:
      
-
        
-
      • Fee
        • 
-
      • Fie
        • 
-
      • Foe
        • 
-
      3. 
-
    3. Third
      4. 
-
    
-
    This was an error in Markdown 1.0.1:
    
-
      
-
    • this
      
-
        
-
      • sub
        • 
-
      
-
      that
      • 
-
    
diff --git a/oldtests/Original/Ordered_and_unordered_lists.markdown b/oldtests/Original/Ordered_and_unordered_lists.markdown
deleted file mode 100644
index 7f3b497..0000000
--- a/oldtests/Original/Ordered_and_unordered_lists.markdown
+++ /dev/null
@@ -1,131 +0,0 @@
-## Unordered
-
-Asterisks tight:
-
-*	asterisk 1
-*	asterisk 2
-*	asterisk 3
-
-
-Asterisks loose:
-
-*	asterisk 1
-
-*	asterisk 2
-
-*	asterisk 3
-
-* * *
-
-Pluses tight:
-
-+	Plus 1
-+	Plus 2
-+	Plus 3
-
-
-Pluses loose:
-
-+	Plus 1
-
-+	Plus 2
-
-+	Plus 3
-
-* * *
-
-
-Minuses tight:
-
--	Minus 1
--	Minus 2
--	Minus 3
-
-
-Minuses loose:
-
--	Minus 1
-
--	Minus 2
-
--	Minus 3
-
-
-## Ordered
-
-Tight:
-
-1.	First
-2.	Second
-3.	Third
-
-and:
-
-1. One
-2. Two
-3. Three
-
-
-Loose using tabs:
-
-1.	First
-
-2.	Second
-
-3.	Third
-
-and using spaces:
-
-1. One
-
-2. Two
-
-3. Three
-
-Multiple paragraphs:
-
-1.	Item 1, graf one.
-
-	Item 2. graf two. The quick brown fox jumped over the lazy dog's
-	back.
-	
-2.	Item 2.
-
-3.	Item 3.
-
-
-
-## Nested
-
-*	Tab
-	*	Tab
-		*	Tab
-
-Here's another:
-
-1. First
-2. Second:
-	* Fee
-	* Fie
-	* Foe
-3. Third
-
-Same thing but with paragraphs:
-
-1. First
-
-2. Second:
-	* Fee
-	* Fie
-	* Foe
-
-3. Third
-
-
-This was an error in Markdown 1.0.1:
-
-*	this
-
-	*	sub
-
-	that
diff --git a/oldtests/Original/README b/oldtests/Original/README
deleted file mode 100644
index 5143258..0000000
--- a/oldtests/Original/README
+++ /dev/null
@@ -1,15 +0,0 @@
-These are from John Gruber's original markdown test suite, via
-Michel Fortin's mdtest.
-
-The html files have been modified slightly in ways that do not affect the
-semantics.  For example, entities are used for quotes in text, and
-blank lines are omitted between block-level tags.
-
-Trailing blank spaces are removed from lines in raw HTML blocks.
-
-The one (insignificant) semantic change is switching the order
-of emph and strong tags in the output for ***strong and emph***.
-
-We have removed Hard-wrapped_paragraphs_with_list-like_lines tests,
-because the new implementation no longer requires a blank line
-before a list.
diff --git a/oldtests/Original/Strong_and_em_together.html b/oldtests/Original/Strong_and_em_together.html
deleted file mode 100644
index 2629594..0000000
--- a/oldtests/Original/Strong_and_em_together.html
+++ /dev/null
@@ -1,4 +0,0 @@
-
    This is strong and em.
    
-
    So is this word.
    
-
    This is strong and em.
    
-
    So is this word.
    
diff --git a/oldtests/Original/Strong_and_em_together.markdown b/oldtests/Original/Strong_and_em_together.markdown
deleted file mode 100644
index 95ee690..0000000
--- a/oldtests/Original/Strong_and_em_together.markdown
+++ /dev/null
@@ -1,7 +0,0 @@
-***This is strong and em.***
-
-So is ***this*** word.
-
-___This is strong and em.___
-
-So is ___this___ word.
diff --git a/oldtests/Original/Tabs.html b/oldtests/Original/Tabs.html
deleted file mode 100644
index 5389bdf..0000000
--- a/oldtests/Original/Tabs.html
+++ /dev/null
@@ -1,19 +0,0 @@
-
      
-
    • this is a list item
-indented with tabs
      • 
-
    • this is a list item
-indented with spaces
      • 
-
    
-
    Code:
    
-
    this code block is indented by one tab
-
    
-
    And:
    
-
        this code block is indented by two tabs
-
    
-
    And:
    
-
    +   this is an example list item
-    indented with tabs
-
-+   this is an example list item
-    indented with spaces
-
    
diff --git a/oldtests/Original/Tabs.markdown b/oldtests/Original/Tabs.markdown
deleted file mode 100644
index 589d113..0000000
--- a/oldtests/Original/Tabs.markdown
+++ /dev/null
@@ -1,21 +0,0 @@
-+	this is a list item
-	indented with tabs
-
-+   this is a list item
-    indented with spaces
-
-Code:
-
-	this code block is indented by one tab
-
-And:
-
-		this code block is indented by two tabs
-
-And:
-
-	+	this is an example list item
-		indented with tabs
-	
-	+   this is an example list item
-	    indented with spaces
diff --git a/oldtests/Original/Tidyness.html b/oldtests/Original/Tidyness.html
deleted file mode 100644
index f2a8ce7..0000000
--- a/oldtests/Original/Tidyness.html
+++ /dev/null
@@ -1,8 +0,0 @@
-
    
-
    A list within a blockquote:
    
-
      
-
    • asterisk 1
      • 
-
    • asterisk 2
      • 
-
    • asterisk 3
      • 
-
    
-
    
diff --git a/oldtests/Original/Tidyness.markdown b/oldtests/Original/Tidyness.markdown
deleted file mode 100644
index 5f18b8d..0000000
--- a/oldtests/Original/Tidyness.markdown
+++ /dev/null
@@ -1,5 +0,0 @@
-> A list within a blockquote:
-> 
-> *	asterisk 1
-> *	asterisk 2
-> *	asterisk 3
diff --git a/oldtests/Tabs/TabConversionUnicode.html b/oldtests/Tabs/TabConversionUnicode.html
deleted file mode 100644
index f596f6a..0000000
--- a/oldtests/Tabs/TabConversionUnicode.html
+++ /dev/null
@@ -1 +0,0 @@
-
    То лпой is a Russian word with a tab inside.
    
diff --git a/oldtests/Tabs/TabConversionUnicode.markdown b/oldtests/Tabs/TabConversionUnicode.markdown
deleted file mode 100644
index 0bd7b52..0000000
--- a/oldtests/Tabs/TabConversionUnicode.markdown
+++ /dev/null
@@ -1 +0,0 @@
-`То лпой` is a Russian word with a tab inside.
-- 
cgit v1.2.3