Initial commit

6 files changed, 204 insertions, 0 deletions

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..e265113
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+report
+venv/
diff --git a/lib/argparse/pathtype.py b/lib/argparse/pathtype.py
new file mode 100644
index 0000000..39128cc
--- /dev/null
+++ b/lib/argparse/pathtype.py
@@ -0,0 +1,63 @@
+# As usual: copied form stack overflow
+# https://stackoverflow.com/a/33181083
+
+from argparse import ArgumentTypeError as err
+import os
+
+
+class PathType(object):
+    def __init__(self, exists=True, type='file', dash_ok=True):
+        """exists:
+                True: a path that does exist
+                False: a path that does not exist, in a valid parent directory
+                None: don't care
+           type: file, dir, symlink, None, or a function returning True for valid paths
+                None: don't care
+           dash_ok: whether to allow "-" as stdin/stdout"""
+
+        assert exists in (True, False, None)
+        assert type in ('file', 'dir', 'symlink', None) or hasattr(type, '__call__')
+
+        self._exists = exists
+        self._type = type
+        self._dash_ok = dash_ok
+
+    def __call__(self, string):
+        if string == '-':
+            # the special argument "-" means sys.std{in,out}
+            if self._type == 'dir':
+                raise err('standard input/output (-) not allowed as directory path')
+            elif self._type == 'symlink':
+                raise err('standard input/output (-) not allowed as symlink path')
+            elif not self._dash_ok:
+                raise err('standard input/output (-) not allowed')
+        else:
+            e = os.path.exists(string)
+            if self._exists:
+                if not e:
+                    raise err("path does not exist: '%s'" % string)
+
+                if self._type is None:
+                    pass
+                elif self._type == 'file':
+                    if not os.path.isfile(string):
+                        raise err("path is not a file: '%s'" % string)
+                elif self._type == 'symlink':
+                    if not os.path.symlink(string):
+                        raise err("path is not a symlink: '%s'" % string)
+                elif self._type == 'dir':
+                    if not os.path.isdir(string):
+                        raise err("path is not a directory: '%s'" % string)
+                elif not self._type(string):
+                    raise err("path not valid: '%s'" % string)
+            else:
+                if not self._exists and e:
+                    raise err("path exists: '%s'" % string)
+
+                p = os.path.dirname(os.path.normpath(string)) or '.'
+                if not os.path.isdir(p):
+                    raise err("parent path is not a directory: '%s'" % p)
+                elif not os.path.exists(p):
+                    raise err("parent directory does not exist: '%s'" % p)
+
+        return string
diff --git a/lib/find_stats.py b/lib/find_stats.py
new file mode 100644
index 0000000..effb5b7
--- /dev/null
+++ b/lib/find_stats.py
@@ -0,0 +1,59 @@
+import os
+from pathlib import Path
+
+from .stats import Statistics
+
+IGNORED_FOLDERS = [
+    'venv',
+]
+
+
+def find_all_files(folder: Path, verbose: bool = False):
+    def gen():
+        for subpath, subfolders, filenames in os.walk(str(folder)):
+            subfolders[:] = [subfolder for subfolder in subfolders if
+                             not (subfolder.startswith('.') or subfolder.lower() in IGNORED_FOLDERS)]
+            current_path = Path(subpath)
+            for file in filenames:
+                file_path = current_path / file
+                if not file.startswith('.'):
+                    yield file_path
+                    if verbose:
+                        print('Scanning', file_path)
+                else:
+                    if verbose:
+                        print('Skipping', file_path)
+
+    return list(gen())
+
+
+def find_stats_for_file(filename: Path, name: str, stats: Statistics):
+    extension = filename.name.split('.')[-1]
+    try:
+        for line in filename.read_text().split('\n'):
+            spaces = False
+            tabs = False
+            while len(line) > 0 and line[0] in [' ', '\t']:
+                if line[0] == ' ':
+                    spaces = True
+                if line[0] == '\t':
+                    tabs = True
+                line = line[1:]
+            if spaces and tabs:
+                stats.add_mixed_line(extension=extension,
+                                     filename=name)
+            elif spaces:
+                stats.add_spaces(extension=extension)
+            elif tabs:
+                stats.add_tabs(extension=extension)
+    except (UnicodeDecodeError, OSError):
+        pass
+
+
+def find_stats(folder: Path, verbose: bool = False) -> Statistics:
+    folder = folder.resolve()
+    files = find_all_files(folder, verbose=verbose)
+    stats = Statistics()
+    for file in files:
+        find_stats_for_file(folder / file, file, stats)
+    return stats
diff --git a/lib/print_stats.py b/lib/print_stats.py
new file mode 100644
index 0000000..9616caa
--- /dev/null
+++ b/lib/print_stats.py
@@ -0,0 +1,17 @@
+from lib.stats import Statistics
+
+
+def print_stats(stats: Statistics, by_extension: bool):
+    print('spaces:', stats.all_spaces)
+    print('tabs:', stats.all_tabs)
+    print('mixed:', stats.all_mixed)
+    if by_extension:
+        for ext in set(stats.space_dict.keys()) | stats.tab_dict.keys() | stats.mixed_line_dict.keys():
+            print(ext + ':')
+            print('  ', 'spaces:', stats.space_dict[ext])
+            print('  ', 'tabs:', stats.tab_dict[ext])
+            print('  ', 'mixed:', stats.mixed_line_dict[ext])
+    if stats.all_mixed > 0:
+        print('files_with_mixed_lines:')
+        for file in stats.mixed_files:
+            print(' -', file)
diff --git a/lib/stats.py b/lib/stats.py
new file mode 100644
index 0000000..42e4461
--- /dev/null
+++ b/lib/stats.py
@@ -0,0 +1,26 @@
+from collections import defaultdict
+from typing import Set
+
+
+class Statistics:
+    def __init__(self):
+        self.space_dict = defaultdict(int)
+        self.tab_dict = defaultdict(int)
+        self.mixed_line_dict = defaultdict(int)
+        self.mixed_files: Set[str] = set()
+        self.all_tabs = 0
+        self.all_spaces = 0
+        self.all_mixed = 0
+
+    def add_spaces(self, extension='', count=1):
+        self.space_dict[extension] += count
+        self.all_spaces += count
+
+    def add_tabs(self, extension='', count=1):
+        self.tab_dict[extension] += count
+        self.all_tabs += count
+
+    def add_mixed_line(self, extension='', count=1, filename=''):
+        self.mixed_line_dict[extension] += count
+        self.mixed_files.add(filename)
+        self.all_mixed += count
diff --git a/main.py b/main.py
new file mode 100755
index 0000000..ff8ad95
--- /dev/null
+++ b/main.py
@@ -0,0 +1,37 @@
+#!/usr/bin/env python3.6
+
+import argparse
+from pathlib import Path
+
+from lib.argparse.pathtype import PathType
+from lib.find_stats import find_stats
+from lib.print_stats import print_stats
+from lib.stats import Statistics
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        prog='tabsvsspaces',
+        description='Shows statistics about the usage of tabs and spaces in a given folder'
+    )
+    parser.add_argument('folder',
+                        type=PathType(type='dir', exists=True))
+    parser.add_argument('--by-extension', '-e',
+                        dest='extension',
+                        action='store_true',
+                        help='show distribution by file extension'
+                        )
+    parser.add_argument('--verbose', '-v',
+                        dest='verbose',
+                        action='store_true',
+                        help='show debug information')
+    ns = parser.parse_args()
+    folder: str = ns.folder
+    extension: bool = ns.extension
+    verbose: bool = ns.verbose
+    stats: Statistics = find_stats(Path(folder), verbose=verbose)
+    print_stats(stats, extension)
+
+
+if __name__ == '__main__':
+    main()