diff options
Diffstat (limited to 'Lib/difflib.py')
| -rw-r--r-- | Lib/difflib.py | 39 |
1 files changed, 18 insertions, 21 deletions
diff --git a/Lib/difflib.py b/Lib/difflib.py index 7eb42a927b0..ae3479d3d85 100644 --- a/Lib/difflib.py +++ b/Lib/difflib.py @@ -30,7 +30,7 @@ __all__ = ['get_close_matches', 'ndiff', 'restore', 'SequenceMatcher', 'Differ','IS_CHARACTER_JUNK', 'IS_LINE_JUNK', 'context_diff', 'unified_diff', 'HtmlDiff', 'Match'] -import heapq +from heapq import nlargest as _nlargest from collections import namedtuple as _namedtuple Match = _namedtuple('Match', 'a b size') @@ -729,7 +729,7 @@ def get_close_matches(word, possibilities, n=3, cutoff=0.6): result.append((s.ratio(), x)) # Move the best scorers to head of list - result = heapq.nlargest(n, result) + result = _nlargest(n, result) # Strip scores for the best n matches return [x for score, x in result] @@ -852,10 +852,9 @@ class Differ: and return true iff the string is junk. The module-level function `IS_LINE_JUNK` may be used to filter out lines without visible characters, except for at most one splat ('#'). It is recommended - to leave linejunk None; as of Python 2.3, the underlying - SequenceMatcher class has grown an adaptive notion of "noise" lines - that's better than any static definition the author has ever been - able to craft. + to leave linejunk None; the underlying SequenceMatcher class has + an adaptive notion of "noise" lines that's better than any static + definition the author has ever been able to craft. - `charjunk`: A function that should accept a string of length 1. The module-level function `IS_CHARACTER_JUNK` may be used to filter out @@ -1298,17 +1297,18 @@ def ndiff(a, b, linejunk=None, charjunk=IS_CHARACTER_JUNK): Compare `a` and `b` (lists of strings); return a `Differ`-style delta. Optional keyword parameters `linejunk` and `charjunk` are for filter - functions (or None): + functions, or can be None: - - linejunk: A function that should accept a single string argument, and + - linejunk: A function that should accept a single string argument and return true iff the string is junk. The default is None, and is - recommended; as of Python 2.3, an adaptive notion of "noise" lines is - used that does a good job on its own. + recommended; the underlying SequenceMatcher class has an adaptive + notion of "noise" lines. - - charjunk: A function that should accept a string of length 1. The - default is module-level function IS_CHARACTER_JUNK, which filters out - whitespace characters (a blank or tab; note: bad idea to include newline - in this!). + - charjunk: A function that accepts a character (string of length + 1), and returns true iff the character is junk. The default is + the module-level function IS_CHARACTER_JUNK, which filters out + whitespace characters (a blank or tab; note: it's a bad idea to + include newline in this!). Tools/scripts/ndiff.py is a command-line front-end to this function. @@ -1410,7 +1410,7 @@ def _mdiff(fromlines, tolines, context=None, linejunk=None, change_re.sub(record_sub_info,markers) # process each tuple inserting our special marks that won't be # noticed by an xml/html escaper. - for key,(begin,end) in sub_info[::-1]: + for key,(begin,end) in reversed(sub_info): text = text[0:begin]+'\0'+key+text[begin:end]+'\1'+text[end:] text = text[2:] # Handle case of add/delete entire line @@ -1448,10 +1448,7 @@ def _mdiff(fromlines, tolines, context=None, linejunk=None, # are a concatenation of the first character of each of the 4 lines # so we can do some very readable comparisons. while len(lines) < 4: - try: - lines.append(next(diff_lines_iterator)) - except StopIteration: - lines.append('X') + lines.append(next(diff_lines_iterator, 'X')) s = ''.join([line[0] for line in lines]) if s.startswith('X'): # When no more lines, pump out any remaining blank lines so the @@ -1514,7 +1511,7 @@ def _mdiff(fromlines, tolines, context=None, linejunk=None, num_blanks_to_yield -= 1 yield ('','\n'),None,True if s.startswith('X'): - raise StopIteration + return else: yield from_line,to_line,True @@ -1679,7 +1676,7 @@ class HtmlDiff(object): tabsize -- tab stop spacing, defaults to 8. wrapcolumn -- column number where lines are broken and wrapped, defaults to None where lines are not wrapped. - linejunk,charjunk -- keyword arguments passed into ndiff() (used to by + linejunk,charjunk -- keyword arguments passed into ndiff() (used by HtmlDiff() to generate the side by side HTML differences). See ndiff() documentation for argument default values and descriptions. """ |