From 6075d540d81d8a8053be940ec0ff106c81c210be Mon Sep 17 00:00:00 2001
From: Jake Howard <git@theorangeone.net>
Date: Tue, 28 Mar 2017 09:21:06 +0100
Subject: [PATCH] Render md using pandoc with references

---
 md_pdf/assets/harverd.csl | 658 ++++++++++++++++++++++++++++++++++++++
 md_pdf/build/cli.py       |   9 +-
 md_pdf/build/pandoc.py    |  35 +-
 test-files/bib.yaml       |   0
 test-files/test.md        |   1 +
 5 files changed, 689 insertions(+), 14 deletions(-)
 create mode 100644 md_pdf/assets/harverd.csl
 create mode 100644 test-files/bib.yaml
 create mode 100644 test-files/test.md

diff --git a/md_pdf/assets/harverd.csl b/md_pdf/assets/harverd.csl
new file mode 100644
index 0000000..23d6744
--- /dev/null
+++ b/md_pdf/assets/harverd.csl
@@ -0,0 +1,658 @@
+<?xml version="1.0" encoding="utf-8"?>
+<style xmlns="http://purl.org/net/xbiblio/csl" class="in-text" version="1.0" demote-non-dropping-particle="never">
+  <info>
+    <title>American Psychological Association 6th edition</title>
+    <title-short>APA</title-short>
+    <id>http://www.zotero.org/styles/apa</id>
+    <link href="http://www.zotero.org/styles/apa" rel="self"/>
+    <link href="http://owl.english.purdue.edu/owl/resource/560/01/" rel="documentation"/>
+    <author>
+      <name>Simon Kornblith</name>
+      <email>simon@simonster.com</email>
+    </author>
+    <contributor>
+      <name>Bruce D'Arcus</name>
+    </contributor>
+    <contributor>
+      <name>Curtis M. Humphrey</name>
+    </contributor>
+    <contributor>
+      <name>Richard Karnesky</name>
+      <email>karnesky+zotero@gmail.com</email>
+      <uri>http://arc.nucapt.northwestern.edu/Richard_Karnesky</uri>
+    </contributor>
+    <contributor>
+      <name>Sebastian Karcher</name>
+    </contributor>
+    <contributor>
+      <name> Brenton M. Wiernik</name>
+      <email>zotero@wiernik.org</email>
+    </contributor>
+    <category citation-format="author-date"/>
+    <category field="psychology"/>
+    <category field="generic-base"/>
+    <updated>2016-09-28T13:09:49+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 xml:lang="en">
+    <terms>
+      <term name="editortranslator" form="short">
+        <single>ed. &amp; trans.</single>
+        <multiple>eds. &amp; trans.</multiple>
+      </term>
+      <term name="translator" form="short">
+        <single>trans.</single>
+        <multiple>trans.</multiple>
+      </term>
+    </terms>
+  </locale>
+  <macro name="container-contributors">
+    <choose>
+      <if type="chapter paper-conference entry-dictionary entry-encyclopedia" match="any">
+        <group delimiter=", ">
+          <names variable="container-author" delimiter=", ">
+            <name and="symbol" initialize-with=". " delimiter=", "/>
+            <label form="short" prefix=" (" text-case="title" suffix=")"/>
+          </names>
+          <names variable="editor translator" delimiter=", ">
+            <name and="symbol" initialize-with=". " delimiter=", "/>
+            <label form="short" prefix=" (" text-case="title" suffix=")"/>
+          </names>
+        </group>
+      </if>
+    </choose>
+  </macro>
+  <macro name="secondary-contributors">
+    <choose>
+      <if type="article-journal chapter paper-conference entry-dictionary entry-encyclopedia" match="none">
+        <group delimiter=", " prefix=" (" suffix=")">
+          <names variable="container-author" delimiter=", ">
+            <name and="symbol" initialize-with=". " delimiter=", "/>
+            <label form="short" prefix=", " text-case="title"/>
+          </names>
+          <names variable="editor translator" delimiter=", ">
+            <name and="symbol" initialize-with=". " delimiter=", "/>
+            <label form="short" prefix=", " text-case="title"/>
+          </names>
+        </group>
+      </if>
+    </choose>
+  </macro>
+  <macro name="author">
+    <names variable="author">
+      <name name-as-sort-order="all" and="symbol" sort-separator=", " initialize-with=". " delimiter=", " delimiter-precedes-last="always"/>
+      <label form="short" prefix=" (" suffix=")" text-case="capitalize-first"/>
+      <substitute>
+        <names variable="editor"/>
+        <names variable="translator"/>
+        <choose>
+          <if type="report">
+            <text variable="publisher"/>
+            <text macro="title"/>
+          </if>
+          <else>
+            <text macro="title"/>
+          </else>
+        </choose>
+      </substitute>
+    </names>
+  </macro>
+  <macro name="author-short">
+    <names variable="author">
+      <name form="short" and="symbol" delimiter=", " initialize-with=". "/>
+      <substitute>
+        <names variable="editor"/>
+        <names variable="translator"/>
+        <choose>
+          <if type="report">
+            <text variable="publisher"/>
+            <text variable="title" form="short" font-style="italic"/>
+          </if>
+          <else-if type="legal_case">
+            <text variable="title" font-style="italic"/>
+          </else-if>
+          <else-if type="book graphic  motion_picture song" match="any">
+            <text variable="title" form="short" font-style="italic"/>
+          </else-if>
+          <else-if type="bill legislation" match="any">
+            <text variable="title" form="short"/>
+          </else-if>
+          <else-if variable="reviewed-author">
+            <choose>
+              <if variable="reviewed-title" match="none">
+                <text variable="title" form="short" font-style="italic" prefix="Review of "/>
+              </if>
+              <else>
+                <text variable="title" form="short" quotes="true"/>
+              </else>
+            </choose>
+          </else-if>
+          <else>
+            <text variable="title" form="short" quotes="true"/>
+          </else>
+        </choose>
+      </substitute>
+    </names>
+  </macro>
+  <macro name="access">
+    <choose>
+      <if type="thesis report" match="any">
+        <choose>
+          <if variable="DOI" match="any">
+            <text variable="DOI" prefix="https://doi.org/"/>
+          </if>
+          <else-if variable="archive" match="any">
+            <group>
+              <text term="retrieved" text-case="capitalize-first" suffix=" "/>
+              <text term="from" suffix=" "/>
+              <text variable="archive" suffix="."/>
+              <text variable="archive_location" prefix=" (" suffix=")"/>
+            </group>
+          </else-if>
+          <else>
+            <group>
+              <text term="retrieved" text-case="capitalize-first" suffix=" "/>
+              <text term="from" suffix=" "/>
+              <text variable="URL"/>
+            </group>
+          </else>
+        </choose>
+      </if>
+      <else>
+        <choose>
+          <if variable="DOI">
+            <text variable="DOI" prefix="https://doi.org/"/>
+          </if>
+          <else>
+            <choose>
+              <if type="webpage">
+                <group delimiter=" ">
+                  <text term="retrieved" text-case="capitalize-first" suffix=" "/>
+                  <group>
+                    <date variable="accessed" form="text" suffix=", "/>
+                  </group>
+                  <text term="from"/>
+                  <text variable="URL"/>
+                </group>
+              </if>
+              <else>
+                <group>
+                  <text term="retrieved" text-case="capitalize-first" suffix=" "/>
+                  <text term="from" suffix=" "/>
+                  <text variable="URL"/>
+                </group>
+              </else>
+            </choose>
+          </else>
+        </choose>
+      </else>
+    </choose>
+  </macro>
+  <macro name="title">
+    <choose>
+      <if type="book graphic manuscript motion_picture report song speech thesis" match="any">
+        <choose>
+          <if variable="version" type="book" match="all">
+            <!---This is a hack until we have a computer program type -->
+            <text variable="title"/>
+          </if>
+          <else>
+            <text variable="title" font-style="italic"/>
+          </else>
+        </choose>
+      </if>
+      <else-if variable="reviewed-author">
+        <choose>
+          <if variable="reviewed-title">
+            <group delimiter=" ">
+              <text variable="title"/>
+              <group delimiter=", " prefix="[" suffix="]">
+                <text variable="reviewed-title" font-style="italic" prefix="Review of "/>
+                <names variable="reviewed-author" delimiter=", ">
+                  <label form="verb-short" suffix=" "/>
+                  <name and="symbol" initialize-with=". " delimiter=", "/>
+                </names>
+              </group>
+            </group>
+          </if>
+          <else>
+            <!-- assume `title` is title of reviewed work -->
+            <group delimiter=", " prefix="[" suffix="]">
+              <text variable="title" font-style="italic" prefix="Review of "/>
+              <names variable="reviewed-author" delimiter=", ">
+                <label form="verb-short" suffix=" "/>
+                <name and="symbol" initialize-with=". " delimiter=", "/>
+              </names>
+            </group>
+          </else>
+        </choose>
+      </else-if>
+      <else>
+        <text variable="title"/>
+      </else>
+    </choose>
+  </macro>
+  <macro name="title-plus-extra">
+    <text macro="title"/>
+    <choose>
+      <if type="report thesis" match="any">
+        <group prefix=" (" suffix=")" delimiter=", ">
+          <group delimiter=" ">
+            <choose>
+              <if variable="genre" match="any">
+                <text variable="genre"/>
+              </if>
+              <else>
+                <text variable="collection-title"/>
+              </else>
+            </choose>
+            <text variable="number" prefix="No. "/>
+          </group>
+          <group delimiter=" ">
+            <text term="version" text-case="capitalize-first"/>
+            <text variable="version"/>
+          </group>
+          <text macro="edition"/>
+        </group>
+      </if>
+      <else-if type="post-weblog webpage" match="any">
+        <text variable="genre" prefix=" [" suffix="]"/>
+      </else-if>
+      <else-if variable="version">
+        <group delimiter=" " prefix=" (" suffix=")">
+          <text term="version" text-case="capitalize-first"/>
+          <text variable="version"/>
+        </group>
+      </else-if>
+    </choose>
+    <text macro="format" prefix=" [" suffix="]"/>
+  </macro>
+  <macro name="format">
+    <choose>
+      <if match="any" variable="medium">
+        <text variable="medium" text-case="capitalize-first"/>
+      </if>
+      <else-if type="dataset" match="any">
+        <text value="Data set"/>
+      </else-if>
+    </choose>
+  </macro>
+  <macro name="publisher">
+    <choose>
+      <if type="report" match="any">
+        <group delimiter=": ">
+          <text variable="publisher-place"/>
+          <text variable="publisher"/>
+        </group>
+      </if>
+      <else-if type="thesis" match="any">
+        <group delimiter=", ">
+          <text variable="publisher"/>
+          <text variable="publisher-place"/>
+        </group>
+      </else-if>
+      <else-if type="post-weblog webpage" match="none">
+        <group delimiter=", ">
+          <choose>
+            <if variable="event version" type="speech motion_picture" match="none">
+              <!-- Including version is to avoid printing the programming language for computerProgram /-->
+              <text variable="genre"/>
+            </if>
+          </choose>
+          <choose>
+            <if type="article-journal article-magazine" match="none">
+              <group delimiter=": ">
+                <choose>
+                  <if variable="publisher-place">
+                    <text variable="publisher-place"/>
+                  </if>
+                  <else>
+                    <text variable="event-place"/>
+                  </else>
+                </choose>
+                <text variable="publisher"/>
+              </group>
+            </if>
+          </choose>
+        </group>
+      </else-if>
+    </choose>
+  </macro>
+  <macro name="event">
+    <choose>
+      <if variable="container-title" match="none">
+        <choose>
+          <if variable="event">
+            <choose>
+              <if variable="genre" match="none">
+                <text term="presented at" text-case="capitalize-first" suffix=" "/>
+                <text variable="event"/>
+              </if>
+              <else>
+                <group delimiter=" ">
+                  <text variable="genre" text-case="capitalize-first"/>
+                  <text term="presented at"/>
+                  <text variable="event"/>
+                </group>
+              </else>
+            </choose>
+          </if>
+          <else-if type="speech">
+            <text variable="genre" text-case="capitalize-first"/>
+          </else-if>
+        </choose>
+      </if>
+    </choose>
+  </macro>
+  <macro name="issued">
+    <choose>
+      <if type="bill legal_case legislation" match="none">
+        <choose>
+          <if variable="issued">
+            <group prefix=" (" suffix=")">
+              <date variable="issued">
+                <date-part name="year"/>
+              </date>
+              <text variable="year-suffix"/>
+              <choose>
+                <if type="speech" match="any">
+                  <date variable="issued">
+                    <date-part prefix=", " name="month"/>
+                  </date>
+                </if>
+                <else-if type="article-journal bill book chapter graphic legal_case legislation motion_picture paper-conference report song dataset" match="none">
+                  <date variable="issued">
+                    <date-part prefix=", " name="month"/>
+                    <date-part prefix=" " name="day"/>
+                  </date>
+                </else-if>
+              </choose>
+            </group>
+          </if>
+          <else-if variable="status">
+            <group prefix=" (" suffix=")">
+              <text variable="status"/>
+              <text variable="year-suffix" prefix="-"/>
+            </group>
+          </else-if>
+          <else>
+            <group prefix=" (" suffix=")">
+              <text term="no date" form="short"/>
+              <text variable="year-suffix" prefix="-"/>
+            </group>
+          </else>
+        </choose>
+      </if>
+    </choose>
+  </macro>
+  <macro name="issued-sort">
+    <choose>
+      <if type="article-journal bill book chapter graphic legal_case legislation motion_picture paper-conference report song dataset" match="none">
+        <date variable="issued">
+          <date-part name="year"/>
+          <date-part name="month"/>
+          <date-part name="day"/>
+        </date>
+      </if>
+      <else>
+        <date variable="issued">
+          <date-part name="year"/>
+        </date>
+      </else>
+    </choose>
+  </macro>
+  <macro name="issued-year">
+    <choose>
+      <if variable="issued">
+        <group delimiter="/">
+          <date variable="original-date" form="text"/>
+          <group>
+            <date variable="issued">
+              <date-part name="year"/>
+            </date>
+            <text variable="year-suffix"/>
+          </group>
+        </group>
+      </if>
+      <else-if variable="status">
+        <text variable="status"/>
+        <text variable="year-suffix" prefix="-"/>
+      </else-if>
+      <else>
+        <text term="no date" form="short"/>
+        <text variable="year-suffix" prefix="-"/>
+      </else>
+    </choose>
+  </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="locators">
+    <choose>
+      <if type="article-journal article-magazine" match="any">
+        <group prefix=", " delimiter=", ">
+          <group>
+            <text variable="volume" font-style="italic"/>
+            <text variable="issue" prefix="(" suffix=")"/>
+          </group>
+          <text variable="page"/>
+        </group>
+        <choose>
+          <!--for advanced online publication-->
+          <if variable="issued">
+            <choose>
+              <if variable="page issue" match="none">
+                <text variable="status" prefix=". "/>
+              </if>
+            </choose>
+          </if>
+        </choose>
+      </if>
+      <else-if type="article-newspaper">
+        <group delimiter=" " prefix=", ">
+          <label variable="page" form="short"/>
+          <text variable="page"/>
+        </group>
+      </else-if>
+      <else-if type="book graphic motion_picture report song chapter paper-conference entry-encyclopedia entry-dictionary" match="any">
+        <group prefix=" (" suffix=")" delimiter=", ">
+          <choose>
+            <if type="report" match="none">
+              <!-- edition for report is included in title-plus-extra /-->
+              <text macro="edition"/>
+            </if>
+          </choose>
+          <choose>
+            <if variable="volume" match="any">
+              <group>
+                <text term="volume" form="short" text-case="capitalize-first" suffix=" "/>
+                <number variable="volume" form="numeric"/>
+              </group>
+            </if>
+            <else>
+              <group>
+                <text term="volume" form="short" plural="true" text-case="capitalize-first" suffix=" "/>
+                <number variable="number-of-volumes" form="numeric" prefix="1&#8211;"/>
+              </group>
+            </else>
+          </choose>
+          <group>
+            <label variable="page" form="short" suffix=" "/>
+            <text variable="page"/>
+          </group>
+        </group>
+      </else-if>
+      <else-if type="legal_case">
+        <group prefix=" (" suffix=")" delimiter=" ">
+          <text variable="authority"/>
+          <choose>
+            <if variable="container-title" match="any">
+              <!--Only print year for cases published in reporters-->
+              <date variable="issued" form="numeric" date-parts="year"/>
+            </if>
+            <else>
+              <date variable="issued" form="text"/>
+            </else>
+          </choose>
+        </group>
+      </else-if>
+      <else-if type="bill legislation" match="any">
+        <date variable="issued" prefix=" (" suffix=")">
+          <date-part name="year"/>
+        </date>
+      </else-if>
+    </choose>
+  </macro>
+  <macro name="citation-locator">
+    <group>
+      <choose>
+        <if locator="chapter">
+          <label variable="locator" form="long" text-case="capitalize-first"/>
+        </if>
+        <else>
+          <label variable="locator" form="short"/>
+        </else>
+      </choose>
+      <text variable="locator" prefix=" "/>
+    </group>
+  </macro>
+  <macro name="container">
+    <choose>
+      <if type="post-weblog webpage" match="none">
+        <group>
+          <choose>
+            <if type="chapter paper-conference entry-encyclopedia" match="any">
+              <text term="in" text-case="capitalize-first" suffix=" "/>
+            </if>
+          </choose>
+          <group delimiter=", ">
+            <text macro="container-contributors"/>
+            <text macro="secondary-contributors"/>
+            <text macro="container-title"/>
+          </group>
+        </group>
+      </if>
+    </choose>
+  </macro>
+  <macro name="container-title">
+    <choose>
+      <if type="article article-journal article-magazine article-newspaper" match="any">
+        <text variable="container-title" font-style="italic" text-case="title"/>
+      </if>
+      <else-if type="bill legal_case legislation" match="none">
+        <text variable="container-title" font-style="italic"/>
+      </else-if>
+    </choose>
+  </macro>
+  <macro name="legal-cites">
+    <choose>
+      <if type="legal_case" match="any">
+        <group prefix=", " delimiter=" ">
+          <choose>
+            <if variable="container-title">
+              <text variable="volume"/>
+              <text variable="container-title"/>
+              <group delimiter=" ">
+                <!--change to label variable="section" as that becomes available -->
+                <text term="section" form="symbol"/>
+                <text variable="section"/>
+              </group>
+              <text variable="page"/>
+            </if>
+            <else>
+              <text variable="number" prefix="No. "/>
+            </else>
+          </choose>
+        </group>
+      </if>
+      <else-if type="bill legislation" match="any">
+        <group delimiter=", " prefix=", ">
+          <choose>
+            <if variable="number">
+              <!--There's a public law number-->
+              <text variable="number" prefix="Pub. L. No. "/>
+              <group delimiter=" ">
+                <!--change to label variable="section" as that becomes available -->
+                <text term="section" form="symbol"/>
+                <text variable="section"/>
+              </group>
+              <group delimiter=" ">
+                <text variable="volume"/>
+                <text variable="container-title"/>
+                <text variable="page-first"/>
+              </group>
+            </if>
+            <else>
+              <group delimiter=" ">
+                <text variable="volume"/>
+                <text variable="container-title"/>
+                <!--change to label variable="section" as that becomes available -->
+                <text term="section" form="symbol"/>
+                <text variable="section"/>
+              </group>
+            </else>
+          </choose>
+        </group>
+      </else-if>
+    </choose>
+  </macro>
+  <macro name="original-date">
+    <choose>
+      <if variable="original-date">
+        <group prefix="(" suffix=")" delimiter=" ">
+          <!---This should be localized-->
+          <text value="Original work published"/>
+          <date variable="original-date" form="text"/>
+        </group>
+      </if>
+    </choose>
+  </macro>
+  <citation et-al-min="6" et-al-use-first="1" et-al-subsequent-min="3" et-al-subsequent-use-first="1" disambiguate-add-year-suffix="true" disambiguate-add-names="true" disambiguate-add-givenname="true" collapse="year" givenname-disambiguation-rule="primary-name">
+    <sort>
+      <key macro="author"/>
+      <key macro="issued-sort"/>
+    </sort>
+    <layout prefix="(" suffix=")" delimiter="; ">
+      <group delimiter=", ">
+        <text macro="author-short"/>
+        <text macro="issued-year"/>
+        <text macro="citation-locator"/>
+      </group>
+    </layout>
+  </citation>
+  <bibliography hanging-indent="true" et-al-min="8" et-al-use-first="6" et-al-use-last="true" entry-spacing="0" line-spacing="2">
+    <sort>
+      <key macro="author"/>
+      <key macro="issued-sort" sort="ascending"/>
+      <key macro="title"/>
+    </sort>
+    <layout>
+      <group suffix=".">
+        <group delimiter=". ">
+          <text macro="author"/>
+          <text macro="issued"/>
+          <text macro="title-plus-extra"/>
+          <text macro="container"/>
+        </group>
+        <text macro="legal-cites"/>
+        <text macro="locators"/>
+        <group delimiter=", " prefix=". ">
+          <text macro="event"/>
+          <text macro="publisher"/>
+        </group>
+      </group>
+      <text macro="access" prefix=" "/>
+      <text macro="original-date" prefix=" "/>
+    </layout>
+  </bibliography>
+</style>
diff --git a/md_pdf/build/cli.py b/md_pdf/build/cli.py
index 0eb2ee2..29f70c9 100644
--- a/md_pdf/build/cli.py
+++ b/md_pdf/build/cli.py
@@ -1,9 +1,14 @@
 import click
 from md_pdf.build.md import read_files
+from md_pdf.build.pandoc import build_document
+
 
 @click.command('build', short_help="Build document")
 @click.argument('in_files', type=click.Path(dir_okay=False, resolve_path=True, writable=True), nargs=-1)
+@click.option('--bibliography', '-b', type=click.Path(dir_okay=False, resolve_path=True, writable=True), default=None)
 @click.option('--output', '-o', type=click.Path(file_okay=False, resolve_path=True, writable=True), default='out/')
-def cli(in_files, output):
+def cli(in_files, bibliography, output):
     data = read_files(in_files)
-    print(data)
+    doc = build_document(data, bibliography)
+    print(doc)
+
diff --git a/md_pdf/build/pandoc.py b/md_pdf/build/pandoc.py
index 9080b10..bfc8826 100644
--- a/md_pdf/build/pandoc.py
+++ b/md_pdf/build/pandoc.py
@@ -1,25 +1,36 @@
 import pypandoc
 from bs4 import BeautifulSoup
+import os.path
+from md_pdf.utils import PROJECT_DIR
 
 
+CSL_FILE = os.path.join(PROJECT_DIR, 'assets', 'harverd.csl')
+
 def fix_references_title(content):
     soup = BeautifulSoup(content, 'html.parser')
-    title = soup.new_tag('h1')
-    title.string = "References"
-    soup.find('div', class_="references").insert_before(title)
+    reference_element = soup.find('div', class_='references')
+    if reference_element is not None:
+        title = soup.new_tag('h1')
+        title.string = "References"
+        reference_element.insert_before(title)
     return soup.prettify()
 
 
-def build_document(files_content):
-    html = pypandoc.convert_text(files_content, 'html', format='md',
-        extra_args=[
-            '-s',
-            '--bibliography=bib.yml',
-            '--csl=harvard.csl'
-        ],
-        filters=[
-            'pandoc-citeproc'
+def build_document(files_content, bibliography):
+    args = [
+        '-s',
+    ]
+    filters = []
+    if bibliography is not None:
+        args += [
+            '--bibliography={}'.format(bibliography),
+            '--csl={}'.format(CSL_FILE)
         ]
+        filters.append('pandoc-citeproc')
+
+    html = pypandoc.convert_text(files_content, 'html', format='md',
+        extra_args=args,
+        filters=filters
     )
 
     return fix_references_title(html)
diff --git a/test-files/bib.yaml b/test-files/bib.yaml
new file mode 100644
index 0000000..e69de29
diff --git a/test-files/test.md b/test-files/test.md
new file mode 100644
index 0000000..8ae0569
--- /dev/null
+++ b/test-files/test.md
@@ -0,0 +1 @@
+# Test