kallithea Changeset - 9cdb81c7b855

Changeset - 9cdb81c7b855

Parent rev.

Child rev.

[Not reviewed]

default

0 1 0

Mads Kiilerich - 8 years ago 2017-10-03 00:14:40
mads@kiilerich.com

diffs: extract _parse_lines as a pure function

1 file changed with 102 insertions and 100 deletions:

kallithea/lib/diffs.py

102

100

0 comments (0 inline, 0 general)

kallithea/lib/diffs.py

➞

Show inline comments

@@ @@ -259,26 +259,24 @@ RENAMED_FILENODE = 4 @@
 COPIED_FILENODE = 5
 CHMOD_FILENODE = 6
 BIN_FILENODE = 7
 class DiffProcessor(object):
     """
     Give it a unified or git diff and it returns a list of the files that were
     mentioned in the diff together with a dict of meta information that
     can be used to render it in a HTML template.
     """
     _diff_git_re = re.compile('^diff --git', re.MULTILINE)
     _chunk_re = re.compile(r'^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@(.*)')
     _newline_marker = re.compile(r'^\\ No newline at end of file')
     def __init__(self, diff, vcs='hg', diff_limit=None, inline_diff=True):
         """
         :param diff:   a text in diff format
         :param vcs: type of version control hg or git
         :param diff_limit: define the size of diff that is considered "big"
             based on that parameter cut off will be triggered, set to None
             to show full diff
         """
         if not isinstance(diff, basestring):
             raise Exception('Diff must be a basestring got %s instead' % type(diff))
@@ @@ -355,25 +353,25 @@ class DiffProcessor(object): @@
                         op = 'D'
                         stats['binary'] = True
                         stats['ops'][DEL_FILENODE] = 'deleted file'
                 # it's not ADD not DELETE
                 if op is None:
                     op = 'M'
                     stats['binary'] = True
                     stats['ops'][MOD_FILENODE] = 'modified file'
             # a real non-binary diff
             if head['a_file'] or head['b_file']:
-                chunks, added, deleted = self._parse_lines(diff_lines)
                 chunks, added, deleted = _parse_lines(diff_lines)
                 stats['binary'] = False
                 stats['added'] = added
                 stats['deleted'] = deleted
                 # explicit mark that it's a modified file
                 if op == 'M':
                     stats['ops'][MOD_FILENODE] = 'modified file'
             else:  # Git binary patch (or empty diff)
                 # Git binary patch
                 if head['bin_patch']:
                     stats['ops'][BIN_FILENODE] = 'binary diff not shown'
                 chunks = []
@@ @@ -427,121 +425,24 @@ class DiffProcessor(object): @@
                         except StopIteration:
                             # add was last line - ok
                             _highlight_inline_diff(delline, addline)
                             raise
                         if peekline['action'] != 'add':
                             # there was only one add line - ok
                             _highlight_inline_diff(delline, addline)
                 except StopIteration:
                     pass
         return _files
     def _parse_lines(self, diff_lines):
         """
         Given an iterator of diff body lines, parse them and return a dict per
         line and added/removed totals.
         """
         added = deleted = 0
         old_line = old_end = new_line = new_end = None
         try:
             chunks = []
             line = diff_lines.next()
             while True:
                 lines = []
                 chunks.append(lines)
                 match = self._chunk_re.match(line)
                 if not match:
                     raise Exception('error parsing diff @@ line %r' % line)
                 gr = match.groups()
                 (old_line, old_end,
                  new_line, new_end) = [int(x or 1) for x in gr[:-1]]
                 old_line -= 1
                 new_line -= 1
                 context = len(gr) == 5
                 old_end += old_line
                 new_end += new_line
                 if context:
                     # skip context only if it's first line
                     if int(gr[0]) > 1:
                         lines.append({
                             'old_lineno': '...',
                             'new_lineno': '...',
                             'action':     'context',
                             'line':       line,
                         })
                 line = diff_lines.next()
                 while old_line < old_end or new_line < new_end:
                     if not line:
                         raise Exception('error parsing diff - empty line at -%s+%s' % (old_line, new_line))
                     affects_old = affects_new = False
                     command = line[0]
                     if command == '+':
                         affects_new = True
                         action = 'add'
                         added += 1
                     elif command == '-':
                         affects_old = True
                         action = 'del'
                         deleted += 1
                     elif command == ' ':
                         affects_old = affects_new = True
                         action = 'unmod'
                     else:
                         raise Exception('error parsing diff - unknown command in line %r at -%s+%s' % (line, old_line, new_line))
                     if not self._newline_marker.match(line):
                         old_line += affects_old
                         new_line += affects_new
                         lines.append({
                             'old_lineno':   affects_old and old_line or '',
                             'new_lineno':   affects_new and new_line or '',
                             'action':       action,
                             'line':         line[1:],
                         })
                     line = diff_lines.next()
                     if self._newline_marker.match(line):
                         # we need to append to lines, since this is not
                         # counted in the line specs of diff
                         lines.append({
                             'old_lineno':   '...',
                             'new_lineno':   '...',
                             'action':       'context',
                             'line':         line,
                         })
                         line = diff_lines.next()
                 if old_line > old_end:
                     raise Exception('error parsing diff - more than %s "-" lines at -%s+%s' % (old_end, old_line, new_line))
                 if new_line > new_end:
                     raise Exception('error parsing diff - more than %s "+" lines at -%s+%s' % (new_end, old_line, new_line))
         except StopIteration:
             pass
         if old_line != old_end or new_line != new_end:
             raise Exception('diff processing broken when old %s<>%s or new %s<>%s line %r' % (old_line, old_end, new_line, new_end, line))
         return chunks, added, deleted
     def stat(self):
         """
         Returns tuple of added, and removed lines for this instance
         """
         return self.adds, self.removes
 _escape_re = re.compile(r'(&)|(<)|(>)|(\t)|(\r)|(?<=.)( \n| $)')
 def _escaper(string):
     """
@@ @@ -621,24 +522,125 @@ def _get_header(vcs, diff_chunk): @@
     elif vcs == 'hg':
         match = _hg_header_re.match(diff_chunk)
     if match is None:
         raise Exception('diff not recognized as valid %s diff' % vcs)
     meta_info = match.groupdict()
     rest = diff_chunk[match.end():]
     if rest and not rest.startswith('@') and not rest.startswith('literal ') and not rest.startswith('delta '):
         raise Exception('cannot parse %s diff header: %r followed by %r' % (vcs, diff_chunk[:match.end()], rest[:1000]))
     diff_lines = (_escaper(m.group(0)) for m in re.finditer(r'.*\n|.+$', rest)) # don't split on \r as str.splitlines do
     return meta_info, diff_lines
 _chunk_re = re.compile(r'^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@(.*)')
 _newline_marker = re.compile(r'^\\ No newline at end of file')
 def _parse_lines(diff_lines):
     """
     Given an iterator of diff body lines, parse them and return a dict per
     line and added/removed totals.
     """
     added = deleted = 0
     old_line = old_end = new_line = new_end = None
     try:
         chunks = []
         line = diff_lines.next()
         while True:
             lines = []
             chunks.append(lines)
             match = _chunk_re.match(line)
             if not match:
                 raise Exception('error parsing diff @@ line %r' % line)
             gr = match.groups()
             (old_line, old_end,
              new_line, new_end) = [int(x or 1) for x in gr[:-1]]
             old_line -= 1
             new_line -= 1
             context = len(gr) == 5
             old_end += old_line
             new_end += new_line
             if context:
                 # skip context only if it's first line
                 if int(gr[0]) > 1:
                     lines.append({
                         'old_lineno': '...',
                         'new_lineno': '...',
                         'action':     'context',
                         'line':       line,
                     })
             line = diff_lines.next()
             while old_line < old_end or new_line < new_end:
                 if not line:
                     raise Exception('error parsing diff - empty line at -%s+%s' % (old_line, new_line))
                 affects_old = affects_new = False
                 command = line[0]
                 if command == '+':
                     affects_new = True
                     action = 'add'
                     added += 1
                 elif command == '-':
                     affects_old = True
                     action = 'del'
                     deleted += 1
                 elif command == ' ':
                     affects_old = affects_new = True
                     action = 'unmod'
                 else:
                     raise Exception('error parsing diff - unknown command in line %r at -%s+%s' % (line, old_line, new_line))
                 if not _newline_marker.match(line):
                     old_line += affects_old
                     new_line += affects_new
                     lines.append({
                         'old_lineno':   affects_old and old_line or '',
                         'new_lineno':   affects_new and new_line or '',
                         'action':       action,
                         'line':         line[1:],
                     })
                 line = diff_lines.next()
                 if _newline_marker.match(line):
                     # we need to append to lines, since this is not
                     # counted in the line specs of diff
                     lines.append({
                         'old_lineno':   '...',
                         'new_lineno':   '...',
                         'action':       'context',
                         'line':         line,
                     })
                     line = diff_lines.next()
             if old_line > old_end:
                 raise Exception('error parsing diff - more than %s "-" lines at -%s+%s' % (old_end, old_line, new_line))
             if new_line > new_end:
                 raise Exception('error parsing diff - more than %s "+" lines at -%s+%s' % (new_end, old_line, new_line))
     except StopIteration:
         pass
     if old_line != old_end or new_line != new_end:
         raise Exception('diff processing broken when old %s<>%s or new %s<>%s line %r' % (old_line, old_end, new_line, new_end, line))
     return chunks, added, deleted
 # Used for inline highlighter word split, must match the substitutions in _escaper
 _token_re = re.compile(r'()(&amp;|&lt;|&gt;|<u>\t</u>|<u class="cr"></u>| <i></i>|\W+?)')
 def _highlight_inline_diff(old, new):
     """
     Highlight simple add/remove in two lines given as info dicts. They are
     modified in place and given markup with <del>/<ins>.
     """
     assert old['action'] == 'del'
     assert new['action'] == 'add'

0 comments (0 inline, 0 general)