summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJonas Smedegaard <dr@jones.dk>2014-12-28 06:50:07 +0100
committerJonas Smedegaard <dr@jones.dk>2014-12-28 06:50:07 +0100
commitd3e794c52bd0797cc38ec171779689b2d195f1a3 (patch)
tree19c045de57b1255c6b9d51171ba26f78cf659e48
parent33d10b0888f498d379ca9a9149ac2c33703e46bf (diff)
Escape URLs more aggressively, and fix unescape after bibliography is resolved.
-rw-r--r--Makefile11
1 files changed, 7 insertions, 4 deletions
diff --git a/Makefile b/Makefile
index 87993c0..b93e378 100644
--- a/Makefile
+++ b/Makefile
@@ -6,14 +6,16 @@ source_basename = EUT/2nd-edition
re_blockquote = s|\n*(</?blockquote>)\n*|\n$$1\n|g
# work around modest URL parsing <https://github.com/jgm/pandoc/issues/1838>
-re_urlencode = s|\bhttps?://[^\s/\|}]+[^\s\"]+?\K([-=]+)|uri_escape($$1, "-=")|eg
+re_urlencode = s|\bhttps?://$$RE{net}{domain}{-nospace}{-rfc1101}(?::\d+)?/\K(\S*?)(?=[.,;]?[\s<\"\|}])|uri_escape(uri_unescape($$1), "^A-Za-z0-9/\.")|eg
templates = template.tex header.tex before.tex after.tex
-filters = ./pandoc-memoir ./pandoc-cs1 ./pandoc-iri
+filters = ./pandoc-memoir ./pandoc-cs1
export PANDOC_CITEPROC_FILE = $(stem).bib
+filters-late = ./pandoc-iri
+
# To produce final document: make -B STATUS=final
STATUS ?= draft
@@ -21,6 +23,7 @@ title = Ensuring utmost transparency
subtitle = Free Software and Open Standards under the Rules of Procedure of the European Parliament
args_filter += $(filters:%=--filter %)
args_filter += $(PANDOC_CITEPROC_FILE:%=--bibliography=%)
+args_filter_late += $(filters-late:%=--filter %)
args_meta += -V lang=english -V langoption=variant=british
args_meta += -M title="$(title) - $(subtitle)"
args_meta += -V title="$(title)"
@@ -44,7 +47,7 @@ download:
wget -O $(stem).raw '$(source_baseurl)w/index.php?title=$(source_basename)&action=edit'
$(stem).mediawiki: $(stem).raw
- perl -0777 -MHTML::Entities -MURI::Escape -p \
+ perl -0777 -MHTML::Entities -MRegexp::Common=net -MURI::Escape -p \
-e 's|.*<textarea[^>]*>||s; s|</textarea.*||s;' \
-e 'decode_entities($$_);' \
-e 's|.*?\n= |= |s;' \
@@ -57,4 +60,4 @@ $(stem).native: $(stem).mediawiki $(filters)
pandoc -f mediawiki $(args_filter) -o $@ $<
$(flavors:%=$(stem)-%.pdf) $(stem).tex: $(stem).native $(templates)
- pandoc $(args_meta) $(args_latex) $(args_$(@:$(stem)-%.pdf=%)) -o $@ $<
+ pandoc $(args_meta) $(args_filter_late) $(args_latex) $(args_$(@:$(stem)-%.pdf=%)) -o $@ $<