Skip to content

Commit

Permalink
Merge pull request #101 from shyamd/fix-pandoc-parsing
Browse files Browse the repository at this point in the history 
Fix pandoc parsing for styles without csl tags
  • Loading branch information
@shyamd
shyamd authored Jan 6, 2022
2 parents 5f59dd2 + 15ff2b3 commit 1e55636
Show file tree
Hide file tree
Showing 4 changed files with 258 additions and 6 deletions.
1 change: 0 additions & 1 deletion .pre-commit-config.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -10,4 +10,3 @@ repos:
rev: stable
hooks:
- id: black
language_version: python3.7
12 changes: 10 additions & 2 deletions mkdocs_bibtex/plugin.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -195,10 +195,17 @@ def to_markdown_pandoc(entry, csl_path):
],
)

# This should cut off the pandoc preamble and ending triple colons
markdown = " ".join(markdown.split("\n")[2:-2])

citation_regex = re.compile(
r"\{\.csl-left-margin\}\[(.*)\]\{\.csl-right-inline\}"
)
citation = citation_regex.findall(" ".join(markdown.split("\n")))[0]
try:

citation = citation_regex.findall(markdown)[0]
except IndexError:
citation = markdown
else:
# Older citeproc-filter version of pandoc
with tempfile.TemporaryDirectory() as tmpdir:
Expand All @@ -219,5 +226,6 @@ def to_markdown_pandoc(entry, csl_path):
filters=["pandoc-citeproc"],
)

citation = markdown.replace("\n", " ")[4:]
citation_regex = re.compile(r"(?:1\.)?(.*)")
citation = citation_regex.findall(markdown.replace("\n", " "))[0]
return citation
12 changes: 9 additions & 3 deletions mkdocs_bibtex/test_plugin.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -23,13 +23,13 @@ def test_unescape_for_arithmatex(self):

self.plugin.unescape_for_arithmatex = True
self.assertIn(
"First Author and Second Author\. Test Title (TT)\. *Testing Journal (TJ)*, 2019",
"First Author and Second Author\\. Test Title (TT)\\. *Testing Journal (TJ)*, 2019",
self.plugin.format_citations(test_data.entries.items())["test"],
)

self.plugin.unescape_for_arithmatex = False
self.assertIn(
"First Author and Second Author\. Test Title \(TT\)\. *Testing Journal \(TJ\)*, 2019",
"First Author and Second Author\\. Test Title \\(TT\\)\\. *Testing Journal \\(TJ\\)*, 2019",
self.plugin.format_citations(test_data.entries.items())["test"],
)

Expand Down Expand Up @@ -87,11 +87,17 @@ def test_full_bibliography(self):
self.plugin.format_citations(test_data.entries.items())
self.assertIn("Author, F. & Author, S", self.plugin.full_bibliography)

self.plugin.csl_file = os.path.join(
test_files_dir, "springer-basic-author-date.csl"
)
self.plugin.format_citations(test_data.entries.items())
self.assertIn("Author F, Author S", self.plugin.full_bibliography)

def test_on_page_markdown(self):
self.plugin.on_config(self.plugin.config)
test_markdown = "This is a citation. [@test]\n\n \\bibliography"

self.assertIn(
"[^1]: First Author and Second Author\. Test title\. *Testing Journal*, 2019\.",
"[^1]: First Author and Second Author\\. Test title\\. *Testing Journal*, 2019\\.",
self.plugin.on_page_markdown(test_markdown, None, None, None),
)
239 changes: 239 additions & 0 deletions test_files/springer-basic-author-date.csl
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,239 @@
<?xml version="1.0" encoding="utf-8"?>
<style xmlns="http://purl.org/net/xbiblio/csl" class="in-text" default-locale="en-US" version="1.0" demote-non-dropping-particle="never">
<info>
<title>Springer - Basic (author-date)</title>
<id>http://www.zotero.org/styles/springer-basic-author-date</id>
<link href="http://www.zotero.org/styles/springer-basic-author-date" rel="self"/>
<link href="http://www.springer.com/cda/content/document/cda_downloaddocument/instruct-authors-e.pdf" rel="documentation"/>
<link href="http://www.springer.com/cda/content/document/cda_downloaddocument/manuscript-guidelines-1.0.pdf" rel="documentation"/>
<!-- This style corresponds to 'Springer Basic' in the pdf document 'Key Style Points' at this url -->
<link href="http://www.springer.com/cda/content/document/cda_downloaddocument/Key_Style_Points_1.0.pdf" rel="documentation"/>
<author>
<name>Jens Allmer</name>
<email>jens@allmer.de</email>
<uri>http://jens.allmer.de</uri>
</author>
<contributor>
<name>Sebastian Karcher</name>
</contributor>
<category citation-format="author-date"/>
<category field="generic-base"/>
<summary>Springer Author Date Style for the disciplines Medicine, Biomedicine, Life Sciences, Chemistry, Geosciences, Computer Science, Engineering, Economics. This style is based on Harvard style and recommendations of the Council of Biology Editors.</summary>
<updated>2019-09-25T12:00:00+00:00</updated>
<rights license="http://creativecommons.org/licenses/by-sa/3.0/">This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 License</rights>
</info>
<locale>
<terms>
<term name="and others">et al</term>
<term name="et-al">et al.</term>
<term name="edition" form="short">edn.</term>
</terms>
</locale>
<macro name="author-short">
<names variable="author">
<name form="short" and="text"/>
<et-al/>
<substitute>
<names variable="editor"/>
<names variable="translator"/>
</substitute>
</names>
</macro>
<macro name="author">
<names variable="author">
<name sort-separator=" " initialize-with="" name-as-sort-order="all" delimiter=", " delimiter-precedes-last="always"/>
<label form="short" strip-periods="true" prefix=" (" suffix=")"/>
<et-al term="and others"/>
<substitute>
<names variable="editor"/>
<names variable="translator"/>
</substitute>
</names>
</macro>
<macro name="edition">
<choose>
<if is-numeric="edition">
<group delimiter=" ">
<number variable="edition" form="ordinal"/>
<text term="edition" form="short"/>
</group>
</if>
<else>
<text variable="edition"/>
</else>
</choose>
</macro>
<macro name="year">
<date variable="issued">
<date-part name="year"/>
</date>
</macro>
<macro name="title">
<choose>
<if type="book">
<group delimiter=". ">
<group delimiter=", ">
<text variable="title"/>
<text macro="edition"/>
</group>
<choose>
<!-- Replace with type="software" as that becomes available -->
<if type="book" match="any" variable="version">
<text variable="version" prefix="Version "/>
</if>
</choose>
</group>
</if>
<else>
<text variable="title"/>
</else>
</choose>
</macro>
<macro name="year-parenth">
<date prefix="(" suffix=")" variable="issued">
<date-part name="year"/>
</date>
</macro>
<citation et-al-min="3" et-al-use-first="1" disambiguate-add-year-suffix="true" collapse="year-suffix" cite-group-delimiter=", ">
<sort>
<key variable="issued"/>
<key macro="author"/>
</sort>
<layout prefix="(" suffix=")" delimiter="; ">
<group delimiter=", ">
<group delimiter=" ">
<text macro="author-short"/>
<text macro="year"/>
</group>
<group delimiter=" ">
<label variable="locator" form="short"/>
<text variable="locator"/>
</group>
</group>
</layout>
</citation>
<bibliography et-al-min="5" et-al-use-first="3" hanging-indent="true">
<sort>
<key macro="author"/>
<key variable="author" sort="ascending"/>
</sort>
<layout>
<group delimiter=" ">
<text macro="author"/>
<text macro="year-parenth"/>
<text macro="title"/>
</group>
<choose>
<!-- Book chapter
Brown B, Aaron M (2001) The politics of nature.
In: Smith J (ed) The rise of modern genomics, 3rd edn.
Wiley, New York, pp 230-257 -->
<if type="chapter paper-conference" match="any">
<group delimiter=" " prefix=". ">
<text term="in" text-case="capitalize-first" suffix=":"/>
<names variable="editor">
<name sort-separator=" " initialize-with="" name-as-sort-order="all" delimiter=", " delimiter-precedes-last="always"/>
<label form="short" strip-periods="true" prefix=" (" suffix=")"/>
</names>
<group delimiter=", ">
<text variable="container-title"/>
<text macro="edition"/>
</group>
</group>
<group prefix=". " delimiter=", ">
<text variable="publisher"/>
<text variable="publisher-place"/>
<group delimiter=" ">
<label variable="page" form="short" strip-periods="true"/>
<text variable="page"/>
</group>
</group>
</if>
<else-if type="article-journal">
<choose>
<if variable="page volume" match="any">
<!-- Journal article
Gamelin FX, Baquet G, Berthoin S, Thevenet D, Nourry C, Nottin S, Bosquet L (2009)
Effect of high intensity intermittent training on heart rate variability in prepubescent children.
Eur J Appl Physiol 105:731-738. doi: 10.1007/s00421-008-0955-8
Ideally, the names of all authors should be provided, but the usage of "et al"
in long author lists will also be accepted:
Smith J, Jones M Jr, Houghton L et al (1999)
Future of health insurance. N Engl J Med 965:325-329 -->
<group prefix=". " delimiter=". ">
<group delimiter=" ">
<text variable="container-title" form="short" strip-periods="true"/>
<group delimiter=":">
<text variable="volume" suffix=":"/>
<text variable="page"/>
</group>
</group>
<text prefix="https://doi.org/" variable="DOI"/>
</group>
</if>
<else>
<!-- Article by DOI
Slifka MK, Whitton JL (2000) Clinical implications of dysregulated cytokine production.
J Mol Med. doi:10.1007/s001090000086 -->
<group prefix=". " delimiter=". ">
<text variable="container-title" form="short" strip-periods="true"/>
<text prefix="https://doi.org/" variable="DOI"/>
</group>
</else>
</choose>
</else-if>
<else-if type="bill book graphic legal_case legislation motion_picture report song" match="any">
<!-- Book
South J, Blass B (2001) The future of modern genomics. Blackwell, London -->
<group delimiter=". ">
<group prefix=". " delimiter=", ">
<text variable="publisher"/>
<text variable="publisher-place"/>
</group>
<group>
<choose>
<if match="any" variable="version">
<text variable="URL" prefix="URL "/>
</if>
</choose>
</group>
</group>
</else-if>
<else-if type="webpage post-weblog post" match="any">
<!-- Online document
Doe J (1999) Title of subordinate document. In: The dictionary of substances and their effects.
Royal Society of Chemistry. Available via DIALOG.
http://www.rsc.org/dose/title of subordinate document. Accessed 15 Jan 1999
Unfortunately, "Royal Society of Chemistry. Available via DIALOG." cannot seem to be mapped here -->
<group prefix=". " delimiter=". ">
<text prefix="In: " variable="container-title" form="short"/>
<text variable="URL"/>
<date variable="accessed">
<date-part prefix="Accessed " name="day" suffix=" "/>
<date-part name="month" form="short" suffix=" " strip-periods="true"/>
<date-part name="year"/>
</date>
</group>
</else-if>
<else-if type="thesis">
<!-- Dissertation
Trent JW (1975) Experimental acute renal failure. Dissertation, University of California -->
<group prefix=". " delimiter=", ">
<text variable="genre" text-case="capitalize-first"/>
<text variable="publisher"/>
</group>
</else-if>
<else>
<!-- None of the provided formats need to add manually (some data provided) -->
<group prefix=". " delimiter=" ">
<text variable="container-title" form="short"/>
<group delimiter=":">
<text variable="volume"/>
<text variable="page"/>
</group>
</group>
</else>
</choose>
</layout>
</bibliography>
</style>

0 comments on commit 1e55636

Please sign in to comment.