gh-118150: difflib: expose autojunk flag from SequenceMatcher to public methods and functions #153959
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -276,6 +276,16 @@ ctypes | |
| (Contributed by Peter Bierma in :gh:`153903`.) | ||
|
|
||
|
|
||
| difflib | ||
| ------- | ||
|
|
||
| * Expose optional ``autojunk`` parameter from :class:`difflib.SequenceMatcher` | ||
| to public functions and class methods in :mod:`difflib`, | ||
| allowing to modify behavior of automatic junk heuristic in this module | ||
| in higher public class methods and functions. | ||
| (Contributed by Tomasz Kazimierczak in :gh:`118150`) | ||
|
|
||
|
|
||
| encodings | ||
| --------- | ||
|
|
||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -664,7 +664,7 @@ def real_quick_ratio(self): | |
| __class_getitem__ = classmethod(GenericAlias) | ||
|
|
||
|
|
||
| def get_close_matches(word, possibilities, n=3, cutoff=0.6, *, autojunk=True): | ||
| """Use SequenceMatcher to return list of the best "good enough" matches. | ||
|
|
||
| word is a sequence for which close matches are desired (typically a | ||
|
|
@@ -698,7 +698,7 @@ def get_close_matches(word, possibilities, n=3, cutoff=0.6): | |
| if not 0.0 <= cutoff <= 1.0: | ||
| raise ValueError("cutoff must be in [0.0, 1.0]: %r" % (cutoff,)) | ||
| result = [] | ||
| s = SequenceMatcher(autojunk=autojunk) | ||
| s.set_seq2(word) | ||
| for x in possibilities: | ||
| s.set_seq1(x) | ||
|
|
@@ -810,7 +810,7 @@ class Differ: | |
| + 5. Flat is better than nested. | ||
| """ | ||
|
|
||
| def __init__(self, linejunk=None, charjunk=None, *, autojunk=True): | ||
| """ | ||
| Construct a text differencer, with optional filters. | ||
|
|
||
|
|
@@ -828,10 +828,13 @@ def __init__(self, linejunk=None, charjunk=None): | |
| module-level function `IS_CHARACTER_JUNK` may be used to filter out | ||
| whitespace characters (a blank or tab; **note**: bad idea to include | ||
| newline in this!). Use of IS_CHARACTER_JUNK is recommended. | ||
| - `autojunk`: automatic junk diff heuristic | ||
| (refer to :class:`SequenceMatcher` for specifics). | ||
| """ | ||
|
|
||
| self.linejunk = linejunk | ||
| self.charjunk = charjunk | ||
| self.autojunk = autojunk | ||
|
|
||
| def compare(self, a, b): | ||
| r""" | ||
|
|
@@ -859,7 +862,7 @@ def compare(self, a, b): | |
| + emu | ||
| """ | ||
|
|
||
| cruncher = SequenceMatcher(self.linejunk, a, b, autojunk=self.autojunk) | ||
| for tag, alo, ahi, blo, bhi in cruncher.get_opcodes(): | ||
| if tag == 'replace': | ||
| g = self._fancy_replace(a, alo, ahi, b, blo, bhi) | ||
|
|
@@ -920,7 +923,7 @@ def _fancy_replace(self, a, alo, ahi, b, blo, bhi): | |
| # Later, more pathological cases prompted removing recursion | ||
| # entirely. | ||
| cutoff = 0.74999 | ||
| cruncher = SequenceMatcher(self.charjunk, autojunk=self.autojunk) | ||
| crqr = cruncher.real_quick_ratio | ||
| cqr = cruncher.quick_ratio | ||
| cr = cruncher.ratio | ||
|
|
@@ -1099,7 +1102,7 @@ def _format_range_unified(start, stop): | |
| return '{},{}'.format(beginning, length) | ||
|
|
||
| def unified_diff(a, b, fromfile='', tofile='', fromfiledate='', | ||
| tofiledate='', n=3, lineterm='\n', *, autojunk=True, color=False): | ||
| r""" | ||
| Compare two sequences of lines; generate the delta as a unified diff. | ||
|
|
||
|
|
@@ -1120,6 +1123,9 @@ def unified_diff(a, b, fromfile='', tofile='', fromfiledate='', | |
| 'git diff --color'. Even if enabled, it can be | ||
| controlled using environment variables such as 'NO_COLOR'. | ||
|
|
||
| Set `autojunk` to False if you don't want automated junk heuristic. | ||
| See details in :class:`SequenceMatcher. | ||
|
|
||
| The unidiff format normally has a header for filenames and modification | ||
| times. Any or all of these may be specified using strings for | ||
| 'fromfile', 'tofile', 'fromfiledate', and 'tofiledate'. | ||
|
|
@@ -1150,7 +1156,7 @@ def unified_diff(a, b, fromfile='', tofile='', fromfiledate='', | |
|
|
||
| _check_types(a, b, fromfile, tofile, fromfiledate, tofiledate, lineterm) | ||
| started = False | ||
| for group in SequenceMatcher(None, a, b, autojunk=autojunk).get_grouped_opcodes(n): | ||
| if not started: | ||
| started = True | ||
| fromdate = '\t{}'.format(fromfiledate) if fromfiledate else '' | ||
|
|
@@ -1193,7 +1199,7 @@ def _format_range_context(start, stop): | |
|
|
||
| # See http://www.unix.org/single_unix_specification/ | ||
| def context_diff(a, b, fromfile='', tofile='', | ||
| fromfiledate='', tofiledate='', n=3, lineterm='\n', *, autojunk=True): | ||
| r""" | ||
| Compare two sequences of lines; generate the delta as a context diff. | ||
|
|
||
|
|
@@ -1216,6 +1222,10 @@ def context_diff(a, b, fromfile='', tofile='', | |
| The modification times are normally expressed in the ISO 8601 format. | ||
| If not specified, the strings default to blanks. | ||
|
|
||
| The kwarg `autojunk` sets up automated junk heuristic with | ||
| :class:`SequenceMatcher`, which is used under the hood in this function. | ||
| See documentation of :class:`SequenceMatcher` for details. | ||
|
|
||
| Example: | ||
|
|
||
| >>> print(''.join(context_diff('one\ntwo\nthree\nfour\n'.splitlines(True), | ||
|
|
@@ -1239,7 +1249,7 @@ def context_diff(a, b, fromfile='', tofile='', | |
| _check_types(a, b, fromfile, tofile, fromfiledate, tofiledate, lineterm) | ||
| prefix = dict(insert='+ ', delete='- ', replace='! ', equal=' ') | ||
| started = False | ||
| for group in SequenceMatcher(None, a, b, autojunk=autojunk).get_grouped_opcodes(n): | ||
| if not started: | ||
| started = True | ||
| fromdate = '\t{}'.format(fromfiledate) if fromfiledate else '' | ||
|
|
@@ -1321,7 +1331,7 @@ def decode(s): | |
| for line in lines: | ||
| yield line.encode('ascii', 'surrogateescape') | ||
|
|
||
| def ndiff(a, b, linejunk=None, charjunk=IS_CHARACTER_JUNK, *, autojunk=True): | ||
| r""" | ||
| Compare `a` and `b` (lists of strings); return a `Differ`-style delta. | ||
|
|
||
|
|
@@ -1339,6 +1349,8 @@ def ndiff(a, b, linejunk=None, charjunk=IS_CHARACTER_JUNK): | |
| whitespace characters (a blank or tab; note: it's a bad idea to | ||
| include newline in this!). | ||
|
|
||
| - autojunk: automatic junk heuristic - refer to :class:`SequenceMatcher` for details | ||
|
|
||
| Tools/scripts/ndiff.py is a command-line front-end to this function. | ||
|
|
||
| Example: | ||
|
|
@@ -1356,10 +1368,10 @@ def ndiff(a, b, linejunk=None, charjunk=IS_CHARACTER_JUNK): | |
| + tree | ||
| + emu | ||
| """ | ||
| return Differ(linejunk, charjunk, autojunk=autojunk).compare(a, b) | ||
|
|
||
| def _mdiff(fromlines, tolines, context=None, linejunk=None, | ||
| charjunk=IS_CHARACTER_JUNK, *, autojunk=True): | ||
| r"""Returns generator yielding marked up from/to side by side differences. | ||
|
|
||
| Arguments: | ||
|
|
@@ -1369,6 +1381,7 @@ def _mdiff(fromlines, tolines, context=None, linejunk=None, | |
| if None, all from/to text lines will be generated. | ||
| linejunk -- passed on to ndiff (see ndiff documentation) | ||
| charjunk -- passed on to ndiff (see ndiff documentation) | ||
| autojunk -- passed on to ndiff (see ndiff documentation) | ||
|
|
||
| This function returns an iterator which returns a tuple: | ||
| (from line tuple, to line tuple, boolean flag) | ||
|
|
@@ -1398,7 +1411,7 @@ def _mdiff(fromlines, tolines, context=None, linejunk=None, | |
| change_re = re.compile(r'(\++|\-+|\^+)') | ||
|
|
||
| # create the difference iterator to generate the differences | ||
| diff_lines_iterator = ndiff(fromlines, tolines, linejunk, charjunk, autojunk=autojunk) | ||
|
|
||
| def _make_line(lines, format_key, side, num_lines=[0,0]): | ||
| """Returns line of text with user's change markup and line formatting. | ||
|
|
@@ -1738,21 +1751,22 @@ class HtmlDiff(object): | |
| _default_prefix = 0 | ||
|
|
||
| def __init__(self,tabsize=8,wrapcolumn=None,linejunk=None, | ||
| charjunk=IS_CHARACTER_JUNK, *, autojunk=True): | ||
| """HtmlDiff instance initializer | ||
|
|
||
| Arguments: | ||
| 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, autojunk -- 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. | ||
| """ | ||
| self._tabsize = tabsize | ||
| self._wrapcolumn = wrapcolumn | ||
| self._linejunk = linejunk | ||
| self._charjunk = charjunk | ||
| self._autojunk = autojunk | ||
|
|
||
| def make_file(self, fromlines, tolines, fromdesc='', todesc='', | ||
| context=False, numlines=5, *, charset='utf-8'): | ||
|
|
@@ -2026,7 +2040,7 @@ def make_table(self,fromlines,tolines,fromdesc='',todesc='',context=False, | |
| else: | ||
| context_lines = None | ||
| diffs = _mdiff(fromlines,tolines,context_lines,linejunk=self._linejunk, | ||
| charjunk=self._charjunk, autojunk=self._autojunk) | ||
|
|
||
| # set up iterator to wrap lines that exceed desired width | ||
| if self._wrapcolumn: | ||
|
|
||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is covered in the individual function/class docs; we don't need to repeat it.
We usually don't link to the issue from versionchanged; that's for NEWS & whatsnew.