Implement Markdown trailing space line break preservation

Markdown uses two or more trailing spaces on a line to indicate a forced
line break `<br/>` - these will be preserved for files with a markdown
extension (default = `.md` or `.markdown`).

Add `--markdown-linebreak-ext=X,Y` to add extensions (`*` matches any),
and `--no-markdown-linebreak-ext` to disable this feature.

If you want to set specific extension `foo` only (and not md/markdown),
use `--no-markdown-linebreak-ext --markdown-linebreak-ext=foo`

Tries to prevent --markdown-linebreak-ext from eating filenames as if they were
extensions by rejecting any with '.' or '/' (or even Windows-style '\' or ':')

Update README.md to include information on these arguments as well as
arguments added to other hooks

Add extensive tests using pytest.mark.parametrize

test that `txt` file is not considered as 'txt' extension
test that `.txt` file is not considered as 'txt' extension

The latter is the (correct) behavior of os.path.splitext(), and an example
of why it is better to use the libraries than to mangle strings yourself.

pre_commit_hooks/detect_private_key.py

@@ -1,10 +1,9 @@
 from __future__ import print_function
 
+import argparse
 import io
 import sys
 
-import argparse
-
 
 def detect_private_key(argv=None):
     parser = argparse.ArgumentParser()

pre_commit_hooks/trailing_whitespace_fixer.py

@@ -2,18 +2,44 @@ from __future__ import print_function
 
 import argparse
 import fileinput
+import os
 import sys
 
 from pre_commit_hooks.util import cmd_output
 
 
-def _fix_file(filename):
+def _fix_file(filename, markdown=False):
     for line in fileinput.input([filename], inplace=True):
+        # preserve trailing two-space for non-blank lines in markdown files
+        if markdown and (not line.isspace()) and (line.endswith("  \n")):
+            line = line.rstrip(' \n')
+            # only preserve if there are no trailing tabs or unusual whitespace
+            if not line[-1].isspace():
+                print(line + "  ")
+                continue
+
         print(line.rstrip())
 
 
 def fix_trailing_whitespace(argv=None):
     parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '--no-markdown-linebreak-ext',
+        action='store_const',
+        const=[],
+        default=argparse.SUPPRESS,
+        dest='markdown_linebreak_ext',
+        help='Do not preserve linebreak spaces in Markdown'
+    )
+    parser.add_argument(
+        '--markdown-linebreak-ext',
+        action='append',
+        const='',
+        default=['md,markdown'],
+        metavar='*|EXT[,EXT,...]',
+        nargs='?',
+        help='Markdown extensions (or *) for linebreak spaces'
+    )
     parser.add_argument('filenames', nargs='*', help='Filenames to fix')
     args = parser.parse_args(argv)
 
@@ -21,10 +47,28 @@ def fix_trailing_whitespace(argv=None):
         'grep', '-l', '[[:space:]]$', *args.filenames, retcode=None
     ).strip().splitlines()
 
+    md_args = args.markdown_linebreak_ext
+    if '' in md_args:
+        parser.error('--markdown-linebreak-ext requires a non-empty argument')
+    all_markdown = '*' in md_args
+    # normalize all extensions; split at ',', lowercase, and force 1 leading '.'
+    md_exts = ['.' + x.lower().lstrip('.')
+               for x in ','.join(md_args).split(',')]
+
+    # reject probable "eaten" filename as extension (skip leading '.' with [1:])
+    for ext in md_exts:
+        if any(c in ext[1:] for c in r'./\:'):
+            parser.error(
+                "bad --markdown-linebreak-ext extension '{0}' (has . / \\ :)\n"
+                "  (probably filename; use '--markdown-linebreak-ext=EXT')"
+                .format(ext)
+            )
+
     if bad_whitespace_files:
         for bad_whitespace_file in bad_whitespace_files:
             print('Fixing {0}'.format(bad_whitespace_file))
-            _fix_file(bad_whitespace_file)
+            _, extension = os.path.splitext(bad_whitespace_file.lower())
+            _fix_file(bad_whitespace_file, all_markdown or extension in md_exts)
         return 1
     else:
         return 0