[Docutils-checkins] SF.net SVN: docutils:[8198] trunk/docutils

[<mi...@us...>]

Revision: 8198
          http://sourceforge.net/p/docutils/code/8198
Author:   milde
Date:     2017-11-04 21:14:37 +0000 (Sat, 04 Nov 2017)
Log Message:
-----------
Ignore backslash-escaped separators when extracting authors from a paragraph.

Modified Paths:
--------------
    trunk/docutils/HISTORY.txt
    trunk/docutils/RELEASE-NOTES.txt
    trunk/docutils/docutils/transforms/frontmatter.py
    trunk/docutils/test/test_transforms/test_docinfo.py

Modified: trunk/docutils/HISTORY.txt
===================================================================
--- trunk/docutils/HISTORY.txt	2017-11-04 10:31:01 UTC (rev 8197)
+++ trunk/docutils/HISTORY.txt	2017-11-04 21:14:37 UTC (rev 8198)
@@ -47,6 +47,8 @@
 * docutils/transforms/frontmatter.py:
 
   - Add field name as class argument to generic docinfo fields unconditionally.
+  - Ignore backslash-escaped separators when extracting authors from a
+    paragraph.
 
 * docutils/transforms/references.py:
 

Modified: trunk/docutils/RELEASE-NOTES.txt
===================================================================
--- trunk/docutils/RELEASE-NOTES.txt	2017-11-04 10:31:01 UTC (rev 8197)
+++ trunk/docutils/RELEASE-NOTES.txt	2017-11-04 21:14:37 UTC (rev 8198)
@@ -58,7 +58,11 @@
 
   - Fixed a bug with the "trim" options of the "unicode" directive.
 
+  - Allow escaping of author-separators in `bibliographic fields`__.
+  
+    __ docs/ref/rst/restructuredtext.html#bibliographic-fields
 
+
 Release 0.14 (2017-08-03)
 =========================
 

Modified: trunk/docutils/docutils/transforms/frontmatter.py
===================================================================
--- trunk/docutils/docutils/transforms/frontmatter.py	2017-11-04 10:31:01 UTC (rev 8197)
+++ trunk/docutils/docutils/transforms/frontmatter.py	2017-11-04 21:14:37 UTC (rev 8198)
@@ -424,6 +424,7 @@
                             base_node=field)
                         raise TransformError
                     title = nodes.title(name, labels[canonical])
+                    title[0].rawsource =  labels[canonical]
                     topics[canonical] = biblioclass(
                         '', title, classes=[canonical], *field[1].children)
                 else:
@@ -503,20 +504,30 @@
             raise
 
     def authors_from_one_paragraph(self, field):
-        text = field[1][0].astext().strip()
+        """Return list of Text nodes for ";"- or ","-separated authornames."""
+        # @@ keep original formatting? (e.g. ``:authors: A. Test, *et-al*``)
+        rawnames = (node.rawsource or node.astext
+                    for node in field[1].traverse(nodes.Text))
+        text = ''.join(rawnames)
         if not text:
             raise TransformError
         for authorsep in self.language.author_separators:
-            authornames = text.split(authorsep)
+            # don't split at escaped `authorsep`:
+            pattern = r'(?<=\\\\)%s|(?<!\\)%s' % (authorsep, authorsep)
+            authornames = re.split(pattern, text)
             if len(authornames) > 1:
                 break
-        authornames = [author.strip() for author in authornames]
-        authors = [[nodes.Text(author)] for author in authornames if author]
+        authornames = ((utils.unescape_rawsource(rawname).strip(),
+                        rawname.strip()) for rawname in authornames)
+        authors = [[nodes.Text(author, rawname)]
+                   for (author, rawname) in authornames if author]
         return authors
 
     def authors_from_bullet_list(self, field):
         authors = []
         for item in field[1][0]:
+            if isinstance(item, nodes.comment):
+                continue
             if len(item) != 1 or not isinstance(item[0], nodes.paragraph):
                 raise TransformError
             authors.append(item[0].children)
@@ -526,7 +537,8 @@
 
     def authors_from_paragraphs(self, field):
         for item in field[1]:
-            if not isinstance(item, nodes.paragraph):
+            if not isinstance(item, (nodes.paragraph, nodes.comment)):
                 raise TransformError
-        authors = [item.children for item in field[1]]
+        authors = [item.children for item in field[1]
+                   if not isinstance(item, nodes.comment)]
         return authors

Modified: trunk/docutils/test/test_transforms/test_docinfo.py
===================================================================
--- trunk/docutils/test/test_transforms/test_docinfo.py	2017-11-04 10:31:01 UTC (rev 8197)
+++ trunk/docutils/test/test_transforms/test_docinfo.py	2017-11-04 21:14:37 UTC (rev 8198)
@@ -230,6 +230,49 @@
             <author>
                 One, Only
 """],
+[r""":Authors: Me\, Myself; **I**
+:Authors: Pac\;Man\\; Ms. Pac\Man; Pac\ Man, Jr.
+:Authors:
+    Here
+
+    The\re
+
+    *Every\ where*
+:Authors: - First\\
+          - Se\ cond
+          - Thir\d
+""",
+"""\
+<document source="test data">
+    <docinfo>
+        <authors>
+            <author>
+                Me, Myself
+            <author>
+                I
+        <authors>
+            <author>
+                Pac;Man\\
+            <author>
+                Ms. PacMan
+            <author>
+                PacMan, Jr.
+        <authors>
+            <author>
+                Here
+            <author>
+                There
+            <author>
+                <emphasis>
+                    Everywhere
+        <authors>
+            <author>
+                First\\
+            <author>
+                Second
+            <author>
+                Third
+"""],
 ["""\
 :Authors:
 

This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.