SF.net SVN: docutils:[9776] trunk

Revision: 9776
          http://sourceforge.net/p/docutils/code/9776
Author:   grubert
Date:     2024-07-22 09:48:35 +0000 (Mon, 22 Jul 2024)
Log Message:
-----------
move non printing breakpoint insertion function into manpage writer

Modified Paths:
--------------
    trunk/docutils/HISTORY.txt
    trunk/docutils/docutils/writers/manpage.py
    trunk/docutils/test/test_writers/test_manpage.py
    trunk/sandbox/manpage-writer/ref-breakpoints.py

Modified: trunk/docutils/HISTORY.txt
===================================================================
--- trunk/docutils/HISTORY.txt	2024-07-19 11:57:06 UTC (rev 9775)
+++ trunk/docutils/HISTORY.txt	2024-07-22 09:48:35 UTC (rev 9776)
@@ -143,6 +143,7 @@
   - Feature-request #105 more informative document comments.
     docutils version in header
   - Stop converting text to full capitals (bug #481).
+  - Add module function insert_URI_breakpoints.
 
 * docutils/writers/null.py
 

Modified: trunk/docutils/docutils/writers/manpage.py
===================================================================
--- trunk/docutils/docutils/writers/manpage.py	2024-07-19 11:57:06 UTC (rev 9775)
+++ trunk/docutils/docutils/writers/manpage.py	2024-07-22 09:48:35 UTC (rev 9776)
@@ -89,7 +89,24 @@
 ..
 """
 
+# see groff_man_style recommends aplying non-printing break points
+# in long URIs.
+NONPRINTING_BREAKPOINT = r'\:'
 
+# after a slash series of
+# after?before at sign
+# after question marks
+# after question ampersands
+# after question number signs
+# (?=.) avoids matching the of string
+# TODO before each dot or a series of
+NONBREAKING_INSERT_RE = re.compile(r'([/@?&#]+)(?=.)')
+
+def insert_URI_breakpoints(s):
+    # TODO only for long URIs ?
+    return NONBREAKING_INSERT_RE.sub( r'\1'+NONPRINTING_BREAKPOINT, s)
+
+
 class Writer(writers.Writer):
     """
     manpage writer class

Modified: trunk/docutils/test/test_writers/test_manpage.py
===================================================================
--- trunk/docutils/test/test_writers/test_manpage.py	2024-07-19 11:57:06 UTC (rev 9775)
+++ trunk/docutils/test/test_writers/test_manpage.py	2024-07-22 09:48:35 UTC (rev 9776)
@@ -17,8 +17,27 @@
     sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
 
 from docutils.core import publish_string
+from docutils.writers.manpage import insert_URI_breakpoints
 
+URI_tests = (
+        ("///abc.de", r"///\:abc.de"),
+        ("/abc.de/", r"/\:abc.de/"),
+        ("http://abc.de", r"http://\:abc.de"),
+        ("http://abc.de/fg", r"http://\:abc.de/\:fg"),
+        ("http://abc.de/fg?q=abc", r"http://\:abc.de/\:fg?\:q=abc"),
+        ("http://abc.de/fg/?q=abc", r"http://\:abc.de/\:fg/?\:q=abc"),
+        ("http://abc.de/fg/?q=abc&me#", r"http://\:abc.de/\:fg/?\:q=abc&\:me#"),
+        ("[email protected]", r"me@\:home.here"),
+        )
 
+class URIBreakpointsTestCase(unittest.TestCase):
+
+    def test_insert(self):
+        for t in URI_tests:
+            got = insert_URI_breakpoints(t[0])
+            self.assertEqual(t[1], got)
+
+
 class WriterPublishTestCase(unittest.TestCase):
 
     maxDiff = None

Modified: trunk/sandbox/manpage-writer/ref-breakpoints.py
===================================================================
--- trunk/sandbox/manpage-writer/ref-breakpoints.py	2024-07-19 11:57:06 UTC (rev 9775)
+++ trunk/sandbox/manpage-writer/ref-breakpoints.py	2024-07-22 09:48:35 UTC (rev 9776)
@@ -1,3 +1,6 @@
+# MOVED to writers.manpage and test.writers.manpage
+# LEFT for reference.
+
 # see groff_man_style on
 
 #  Hyperlink macros
@@ -32,6 +35,8 @@
 #      vers.
 #      
 
+from docutils.writers.manpage import insert_URI_breakpoints
+
 tests = (
         ("///abc.de", r"///\:abc.de"),
         ("/abc.de/", r"/\:abc.de/"),
@@ -43,27 +48,20 @@
         ("[email protected]", r"me@\:home.here"),
         )
 
-import re
-
-BREAKPOINT = r'\:'
-
-# after series of slash
+# after a slash series of
 # after?before at sign
 # after question marks
 # after question ampersands
 # after question number signs
 # (?=.) avoids matching the of string
-MATCH = re.compile(r'([/@?&#]+)(?=.)')
+# TODO before each dot or a series of
 
-def insert_breakpoints(s):
-    return MATCH.sub( r'\1'+BREAKPOINT, s)
-
 err = 0
 cnt = 0
 
 for t in tests:
     cnt += 1
-    got = insert_breakpoints(t[0])
+    got = insert_URI_breakpoints(t[0])
     if t[1] != got:
         print( "FAIL {0} got {1} expected {2}".format(t[0], got, t[1]) )
         err += 1

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