Merge pull request #30 from craigds/bin-script

Add `cchardetect` CLI script

.gitignore

@@ -10,7 +10,6 @@ dist
 build
 eggs
 parts
-bin
 var
 sdist
 develop-eggs

TODO.md

@@ -1,2 +1 @@
-- Implement cli tool (like chardet cli)
 - Improve docs

bin/cchardetect

@@ -0,0 +1,32 @@
+#!/usr/bin/env python
+from __future__ import print_function, unicode_literals
+import argparse
+import cchardet
+
+
+def read_chunks(f, chunk_size):
+    chunk = f.read(chunk_size)
+    while chunk:
+        yield chunk
+        chunk = f.read(chunk_size)
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('files', nargs='+', help="Files to detect encoding of", type=argparse.FileType('rb'))
+    parser.add_argument('--chunk-size', type=int, default=(256 * 1024))
+    args = parser.parse_args()
+
+    for f in args.files:
+        detector = cchardet.UniversalDetector()
+        for chunk in read_chunks(f, args.chunk_size):
+            detector.feed(chunk)
+        detector.close()
+        print('{file.name}: {result[encoding]} with confidence {result[confidence]}'.format(
+            file=f,
+            result=detector.result
+        ))
+
+
+if __name__ == '__main__':
+    main()

setup.py

@@ -137,6 +137,7 @@ setup(
     cmdclass={'build_ext': build_ext},
     package_dir={'': 'src'},
     packages=['cchardet', ],
+    scripts=['bin/cchardetect'],
     ext_modules=[
         cchardet_module
     ],