[PATCH 2 of 3] tests: simplify and document the sorting of pyflake messages

[Simon Heimberg]

# HG changeset patch
# User Simon Heimberg <simohe at besonet.ch>
# Date 1372281175 -7200
# Node ID fd803f71beba3b8e63920f74952b3193810a7413
# Parent  2903c22bb19627574177c38d281e37111ef6a564
tests: simplify and document the sorting of pyflake messages

The pyflake messages are simply ordered by message type, path, line no (and
message text).
The message type is taken from the order of the filters.

The previous ordering looks complicated and illogically.
It was the following order (r'\3:\5:\4:\1:\2:' + line):
  message (\3 and \5)
  var name (\4)
  path (\1)
  line no (\2)
  line reference
Ordering by var name before path looks illogically for me.

diff -r 2903c22bb196 -r fd803f71beba tests/filterpyflakes.py
--- a/tests/filterpyflakes.py	Mit Jun 26 23:06:46 2013 +0200
+++ b/tests/filterpyflakes.py	Mit Jun 26 23:12:55 2013 +0200
@@ -4,35 +4,48 @@
 
 import sys, re, os
 
-def makekey(message):
-    # "path/file:line: message"
-    match = re.search(r"(line \d+)", message)
-    line = ''
-    if match:
-        line = match.group(0)
-        message = re.sub(r"(line \d+)", '', message)
-    return re.sub(r"([^:]*):([^:]+):([^']*)('[^']*')(.*)$",
-                  r'\3:\5:\4:\1:\2:' + line,
-                  message)
+def makekey(typeandline):
+    """
+    for sorting lines by: msgtype, path/to/file, lineno, message
+
+    typeandline is a sequence of a message type and the entire message line
+    the message line format is path/to/file:line: message
+
+    >>> makekey((3, 'example.py:36: any message'))
+    (3, 'example.py', 36, ' any message')
+    >>> makekey((7, 'path/to/file.py:68: dummy message'))
+    (7, 'path/to/file.py', 68, ' dummy message')
+    >>> makekey((2, 'fn:88: m')) > makekey((2, 'fn:9: m'))
+    True
+    """
+
+    msgtype, line = typeandline
+    fname, line, message = line.split(":", 2)
+    # line as int for ordering 9 before 88
+    return msgtype, fname, int(line), message
+
 
 lines = []
 for line in sys.stdin:
-    # We whitelist tests
+    # We whitelist tests (see more messages in pyflakes.messages)
     pats = [
             r"imported but unused",
             r"local variable '.*' is assigned to but never used",
             r"unable to detect undefined names",
            ]
-    if not re.search('|'.join(pats), line):
-        continue
+    for msgtype, pat in enumerate(pats):
+        if re.search(pat, line):
+            break # pattern matches
+    else:
+        continue # no pattern matched, next line
     fn = line.split(':', 1)[0]
     f = open(os.path.join(os.path.dirname(os.path.dirname(__file__)), fn))
     data = f.read()
     f.close()
     if 'no-check-code' in data:
         continue
-    lines.append(line)
+    lines.append((msgtype, line))
 
-for line in sorted(lines, key = makekey):
+for msgtype, line in sorted(lines, key = makekey):
     sys.stdout.write(line)
 print