[Epydoc-commits] SF.net SVN: epydoc: [1574] trunk/epydoc/src/epydoc

[<dva...@us...>]

Revision: 1574
          http://svn.sourceforge.net/epydoc/?rev=1574&view=rev
Author:   dvarrazzo
Date:     2007-03-06 18:55:14 -0800 (Tue, 06 Mar 2007)

Log Message:
-----------
- Fixed summarization for plaintext markup.

  If a docstring had one (or more) line not ending with a full stop, but
  separated from the rest of the docstring by a blank line, and there was a 
  full stop somewhere in the following paragraphs, the docstring was summarized 
  up to the full stop instead of the blank line.  Such docstrings appear in 
  many places in the stdlib.

  - Test case added.

- Pre-compiling the regular expression to recognize the summary.

Modified Paths:
--------------
    trunk/epydoc/src/epydoc/markup/epytext.py
    trunk/epydoc/src/epydoc/markup/javadoc.py
    trunk/epydoc/src/epydoc/markup/plaintext.py
    trunk/epydoc/src/epydoc/markup/restructuredtext.py
    trunk/epydoc/src/epydoc/test/plaintext.doctest

Modified: trunk/epydoc/src/epydoc/markup/epytext.py
===================================================================
--- trunk/epydoc/src/epydoc/markup/epytext.py	2007-03-07 01:26:50 UTC (rev 1573)
+++ trunk/epydoc/src/epydoc/markup/epytext.py	2007-03-07 02:55:14 UTC (rev 1574)
@@ -1969,6 +1969,8 @@
             # Assume that anything else can be passed through.
             return childstr
 
+    _SUMMARY_RE = re.compile(r'(\s*[\w\W]*?\.)(\s|$)')
+
     def summary(self):
         if self._tree is None: return self, False
         tree = self._tree
@@ -2008,7 +2010,7 @@
         doc.children.append(para)
         for parachild in parachildren:
             if isinstance(parachild, basestring):
-                m = re.match(r'(\s*[\w\W]*?\.)(\s|$)', parachild)
+                m = self._SUMMARY_RE.match(parachild)
                 if m:
                     para.children.append(m.group(1))
                     long_docs |= parachild is not parachildren[-1]

Modified: trunk/epydoc/src/epydoc/markup/javadoc.py
===================================================================
--- trunk/epydoc/src/epydoc/markup/javadoc.py	2007-03-07 01:26:50 UTC (rev 1573)
+++ trunk/epydoc/src/epydoc/markup/javadoc.py	2007-03-07 02:55:14 UTC (rev 1574)
@@ -219,13 +219,15 @@
     def to_plaintext(self, docstring_linker, **options):
         return self._docstring
 
+    _SUMMARY_RE = re.compile(r'(\s*[\w\W]*?\.)(\s|$)')
+
     # Jeff's hack to get summary working
     def summary(self):
         # Drop tags
         doc = "\n".join([ row for row in self._docstring.split('\n')
                           if not row.lstrip().startswith('@') ])
 
-        m = re.match(r'(\s*[\w\W]*?\.)(\s|$)', doc)
+        m = self._SUMMARY_RE.match(doc)
         if m:
             other = doc[m.end():]
             return (ParsedJavadocDocstring(m.group(1)),

Modified: trunk/epydoc/src/epydoc/markup/plaintext.py
===================================================================
--- trunk/epydoc/src/epydoc/markup/plaintext.py	2007-03-07 01:26:50 UTC (rev 1573)
+++ trunk/epydoc/src/epydoc/markup/plaintext.py	2007-03-07 02:55:14 UTC (rev 1574)
@@ -50,8 +50,10 @@
             return '\n'.join([' '*indent+l for l in lines])+'\n'
         return self._text+'\n'
     
+    _SUMMARY_RE = re.compile(r'(\s*[\w\W]*?(?:\.(\s|$)|[\n][\t ]*[\n]))')
+
     def summary(self):
-        m = re.match(r'(\s*[\w\W]*?\.)(\s|$)', self._text)
+        m = self._SUMMARY_RE.match(self._text)
         if m:
             other = self._text[m.end():]
             return (ParsedPlaintextDocstring(m.group(1), verbatim=0),

Modified: trunk/epydoc/src/epydoc/markup/restructuredtext.py
===================================================================
--- trunk/epydoc/src/epydoc/markup/restructuredtext.py	2007-03-07 01:26:50 UTC (rev 1573)
+++ trunk/epydoc/src/epydoc/markup/restructuredtext.py	2007-03-07 02:55:14 UTC (rev 1574)
@@ -291,6 +291,7 @@
     def visit_document(self, node):
         self.summary = None
         
+    _SUMMARY_RE = re.compile(r'(\s*[\w\W]*?\.)(\s|$)')
     def visit_paragraph(self, node):
         if self.summary is not None:
             # found a paragraph after the first one
@@ -302,7 +303,7 @@
         # Extract the first sentence.
         for child in node:
             if isinstance(child, docutils.nodes.Text):
-                m = re.match(r'(\s*[\w\W]*?\.)(\s|$)', child.data)
+                m = self._SUMMARY_RE.match(child.data)
                 if m:
                     summary_pieces.append(docutils.nodes.Text(m.group(1)))
                     other = child.data[m.end():]

Modified: trunk/epydoc/src/epydoc/test/plaintext.doctest
===================================================================
--- trunk/epydoc/src/epydoc/test/plaintext.doctest	2007-03-07 01:26:50 UTC (rev 1573)
+++ trunk/epydoc/src/epydoc/test/plaintext.doctest	2007-03-07 02:55:14 UTC (rev 1574)
@@ -52,3 +52,19 @@
 ... This is detached
 ... """)
 ('Other lines without period...', True)
+
+In 3.0beta1 docstrings such this were not correctly summarized.
+
+>>> getsummary("""A user-defined wrapper around string objects
+...
+... Note: string objects have grown methods in Python 1.6
+... This module requires Python 1.6 or later.
+... """)
+('A user-defined wrapper around string objects', True)
+
+>>> getsummary("""This is more tricky
+... than the test before
+...
+... but i am looking for the same bug.
+... """)
+('This is more tricky\nthan the test before', True)


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