diffcount.py

diffcount.py

#!/usr/bin/env python

import sys
import re
import configparser
from fnmatch import fnmatch
from unidiff import PatchSet

EXTS = ["py"]


class Opts:  # pylint: disable=too-few-public-methods
    debug = False
    exclude = []


def filtered_hunks(fil):
    path_re = ".*[.](%s)$" % "|".join(EXTS)
    for patch in PatchSet(fil):
        if not re.match(path_re, patch.path):
            continue
        excluded = False
        if Opts.exclude:
            if Opts.debug:
                print(">", patch.path, "=~", Opts.exclude)
            for ex in Opts.exclude:
                if fnmatch(patch.path, ex):
                    excluded = True
        if excluded:
            continue
        for hunk in patch:
            yield hunk


class Typ:  # pylint: disable=too-few-public-methods
    LINE = "."
    COMMENT = "#"
    DOCSTRING = "d"
    WHITE = "w"


def classify_lines(fil):
    for hunk in filtered_hunks(fil):
        yield from classify_hunk(hunk)


def classify_line(lval):
    """Classify a single python line, noting comments, best efforts at docstring start/stop and pure-whitespace."""
    lval = lval.rstrip("\n\r")
    remaining_lval = lval
    typ = Typ.LINE
    if re.match(r"^ *$", lval):
        return Typ.WHITE, None, ""

    if re.match(r"^ *#", lval):
        typ = Typ.COMMENT
        remaining_lval = ""
    else:
        slug = re.match(r"^ *(\"\"\"|''')(.*)", lval)
        if slug:
            remaining_lval = slug[2]
            slug = slug[1]
            return Typ.DOCSTRING, slug, remaining_lval
    return typ, None, remaining_lval


def classify_hunk(hunk):
    """Classify lines of a python diff-hunk, attempting to note comments and docstrings.

    Ignores context lines.
    Docstring detection is not guaranteed (changes in the middle of large docstrings won't have starts.)
    Using ast would fix, but seems like overkill, and cannot be done on a diff-only.
    """

    p = ""
    prev_typ = 0
    pslug = None
    for line in hunk:
        lval = line.value
        lval = lval.rstrip("\n\r")
        typ = Typ.LINE
        naive_typ, slug, remaining_lval = classify_line(lval)
        if p and p[-1] == "\\":
            typ = prev_typ
        else:
            if prev_typ != Typ.DOCSTRING and naive_typ == Typ.COMMENT:
                typ = naive_typ
            elif naive_typ == Typ.DOCSTRING:
                if prev_typ == Typ.DOCSTRING and pslug == slug:
                    # remainder of line could have stuff on it
                    typ, _, _ = classify_line(remaining_lval)
                else:
                    typ = Typ.DOCSTRING
                    pslug = slug
            elif prev_typ == Typ.DOCSTRING:
                # continue docstring found in this context/hunk
                typ = Typ.DOCSTRING

        p = lval
        prev_typ = typ

        if typ == Typ.DOCSTRING:
            if re.match(r"(%s) *$" % pslug, remaining_lval):
                prev_typ = Typ.LINE

        if line.is_context:
            continue

        yield typ, lval


def count_lines(fil):
    """Totals changed lines of python code, attempting to strip comments and docstrings.

    Deletes/adds are counted equally.
    Could miss some things, don't rely on exact counts.
    """

    count = 0

    for (typ, line) in classify_lines(fil):
        if Opts.debug:
            print(typ, line)
        if typ == Typ.LINE:
            count += 1

    return count


def main():
    Opts.debug = "--debug" in sys.argv
    Opts.exclude = []

    use_covrc = "--covrc" in sys.argv

    if use_covrc:
        config = configparser.ConfigParser()
        config.read(".coveragerc")
        cfg = {s: dict(config.items(s)) for s in config.sections()}
        exclude = cfg.get("report", {}).get("omit", [])
        Opts.exclude = [f.strip() for f in exclude.split("\n") if f.strip()]

    for i in range(len(sys.argv)):
        if sys.argv[i] == "--exclude":
            Opts.exclude.append(sys.argv[i + 1])

    if Opts.debug and Opts.exclude:
        print("--exclude", Opts.exclude)

    print(count_lines(sys.stdin))


example = '''
diff --git a/cryptvfs.py b/cryptvfs.py
index c68429cf6..ee90ecea8 100755
--- a/cryptvfs.py
+++ b/cryptvfs.py
@@ -2,5 +2,17 @@

 from src.main import proc_entry

-if __name__ == "__main__":
-    proc_entry()
+
+
+class Foo:
+    """some docstring
+    """
+    # some comment
+    pass
+
+class Bar:
+    """some docstring
+    """
+    # some comment
+    def method():
+        line1 + 1
'''


def strio(s):
    import io

    return io.StringIO(s)


def test_basic():
    assert count_lines(strio(example)) == 10


def test_main(capsys):
    sys.argv = []
    sys.stdin = strio(example)
    main()
    cap = capsys.readouterr()
    print(cap.out)
    assert cap.out == "10\n"


def test_debug(capsys):
    sys.argv = ["--debug"]
    sys.stdin = strio(example)
    main()
    cap = capsys.readouterr()
    print(cap.out)
    assert Typ.DOCSTRING + '     """some docstring' in cap.out


def test_exclude(capsys):
    sys.argv = ["--exclude", "cryptvfs.py"]
    sys.stdin = strio(example)
    main()
    cap = capsys.readouterr()
    print(cap.out)
    assert cap.out == "0\n"


def test_covrc(capsys):
    sys.argv = ["--covrc"]
    sys.stdin = strio(example)
    main()
    cap = capsys.readouterr()
    print(cap.out)
    assert cap.out == "10\n"


if __name__ == "__main__":
    main()