mercurial/cmdutil.py

10607:f3ac9d6105ee

        repo.ui.progress(_('looking for similarities'), i, total=len(removed))
        if r not in ctx:
            continue
        fctx = ctx.filectx(r)

        def score(text):
            if not len(text):
                return 0.0
            if not fctx.cmp(text):
                return 1.0
            if threshold == 1.0:
                return 0.0
            orig = fctx.data()
            # bdiff.blocks() returns blocks of matching lines
            # count the number of bytes in each
            equal = 0
            alines = mdiff.splitnewlines(text)
            matches = bdiff.blocks(text, orig)
            for x1, x2, y1, y2 in matches:
                for line in alines[x1:x2]:
                    equal += len(line)

            lengths = len(text) + len(orig)
            return equal * 2.0 / lengths

10608:87fce8c5e29d

        repo.ui.progress(_('looking for similarities'), i, total=len(removed))
        if r not in ctx:
            continue
        fctx = ctx.filectx(r)

        # lazily load text
        @util.cachefunc
        def data():
            orig = fctx.data()
            return orig, mdiff.splitnewlines(orig)

        def score(text):
            if not len(text):
                return 0.0
            if not fctx.cmp(text):
                return 1.0
            if threshold == 1.0:
                return 0.0
            orig, lines = data()
            # bdiff.blocks() returns blocks of matching lines
            # count the number of bytes in each
            equal = 0
            matches = bdiff.blocks(text, orig)
            for x1, x2, y1, y2 in matches:
                for line in lines[y1:y2]:
                    equal += len(line)

            lengths = len(text) + len(orig)
            return equal * 2.0 / lengths