Merge pull request #96 from goosemo/feature/Allow-recursing-directories

Feature/allow recursing directories

Author: subsetpark

pycco/main.py

@@ -244,7 +244,8 @@ def highlight(sections, language, preserve_paths=True, outdir=None):
     output = output.replace(highlight_start, "").replace(highlight_end, "")
     fragments = re.split(language["divider_html"], output)
     for i, section in enumerate(sections):
-        section["code_html"] = highlight_start + shift(fragments, "") + highlight_end
+        section["code_html"] = highlight_start + \
+            shift(fragments, "") + highlight_end
         try:
             docs_text = unicode(section["docs_text"])
         except UnicodeError:
@@ -280,7 +281,8 @@ def generate_html(source, sections, preserve_paths=True, outdir=None):
     csspath = path.relpath(path.join(outdir, "pycco.css"), path.split(dest)[0])
 
     for sect in sections:
-        sect["code_html"] = re.sub(r"\{\{", r"__DOUBLE_OPEN_STACHE__", sect["code_html"])
+        sect["code_html"] = re.sub(
+            r"\{\{", r"__DOUBLE_OPEN_STACHE__", sect["code_html"])
 
     rendered = pycco_template({
         "title": title,
@@ -364,7 +366,8 @@ def generate_html(source, sections, preserve_paths=True, outdir=None):
 
     # The mirror of `divider_text` that we expect Pygments to return. We can split
     # on this to recover the original sections.
-    l["divider_html"] = re.compile(r'\n*<span class="c[1]?">' + l["symbol"] + 'DIVIDER</span>\n*')
+    l["divider_html"] = re.compile(
+        r'\n*<span class="c[1]?">' + l["symbol"] + 'DIVIDER</span>\n*')
 
     # Get the Pygments Lexer for this language.
     l["lexer"] = lexers.get_lexer_by_name(l["name"])
@@ -438,7 +441,8 @@ def remove_control_chars(s):
     # Sanitization regexp copied from
     # http://stackoverflow.com/questions/92438/stripping-non-printable-characters-from-a-string-in-python
     from pycco.compat import pycco_unichr
-    control_chars = ''.join(map(pycco_unichr, list(range(0, 32)) + list(range(127, 160))))
+    control_chars = ''.join(
+        map(pycco_unichr, list(range(0, 32)) + list(range(127, 160))))
     control_char_re = re.compile(u'[{}]'.format(re.escape(control_chars)))
     return control_char_re.sub('', s)
 
@@ -461,6 +465,23 @@ def ensure_directory(directory):
 highlight_end = "</pre></div>"
 
 
+def _flatten_sources(sources):
+    """
+    This function will iterate through the list of sources and if a directory
+    is encountered it will walk the tree for any files
+    """
+    _sources = []
+
+    for source in sources:
+        if os.path.isdir(source):
+            for dirpath, _, filenames in os.walk(source):
+                _sources.extend([os.path.join(dirpath, f) for f in filenames])
+        else:
+            _sources.append(source)
+
+    return _sources
+
+
 def process(sources, preserve_paths=True, outdir=None, language=None, encoding="utf8", index=False):
     """For each source file passed as argument, generate the documentation."""
 
@@ -469,7 +490,7 @@ def process(sources, preserve_paths=True, outdir=None, language=None, encoding="
 
     # Make a copy of sources given on the command line. `main()` needs the
     # original list when monitoring for changed files.
-    sources = sorted(sources)
+    sources = sorted(_flatten_sources(sources))
 
     # Proceed to generating the documentation.
     if sources:

tests/test_pycco.py

@@ -33,7 +33,8 @@ def test_shift(fragments, default):
 @given(text(), booleans(), text(min_size=1))
 @example("/foo", True, "0")
 def test_destination(filepath, preserve_paths, outdir):
-    dest = p.destination(filepath, preserve_paths=preserve_paths, outdir=outdir)
+    dest = p.destination(
+        filepath, preserve_paths=preserve_paths, outdir=outdir)
     assert dest.startswith(outdir)
     assert dest.endswith(".html")
 
@@ -65,12 +66,14 @@ def test_comment_with_only_cross_ref():
     source = '''# ==Link Target==\n\ndef test_link():\n    """[[testing.py#link-target]]"""\n    pass'''
     sections = p.parse(source, PYTHON)
     p.highlight(sections, PYTHON, outdir=tempfile.gettempdir())
-    assert sections[1]['docs_html'] == '<p><a href="testing.html#link-target">testing.py</a></p>'
+    assert sections[1][
+        'docs_html'] == '<p><a href="testing.html#link-target">testing.py</a></p>'
 
 
 @given(text(), text())
 def test_get_language_specify_language(source, code):
-    assert p.get_language(source, code, language="python") == p.languages['.py']
+    assert p.get_language(
+        source, code, language="python") == p.languages['.py']
 
     with pytest.raises(ValueError):
         p.get_language(source, code, language="non-existent")
@@ -99,7 +102,8 @@ def test_get_language_bad_code(code):
 
 @given(text(max_size=64))
 def test_ensure_directory(dir_name):
-    tempdir = os.path.join(tempfile.gettempdir(), str(int(time.time())), dir_name)
+    tempdir = os.path.join(tempfile.gettempdir(),
+                           str(int(time.time())), dir_name)
 
     # Use sanitization from function, but only for housekeeping. We
     # pass in the unsanitized string to the function.
@@ -161,3 +165,26 @@ def test_generate_index(path_lists, outdir_list):
     file_paths = [os.path.join(*path_list) for path_list in path_lists]
     outdir = os.path.join(*outdir_list)
     generate_index.generate_index(file_paths, outdir=outdir)
+
+
+def test_flatten_sources(tmpdir):
+    sources = [str(tmpdir)]
+    expected_sources = []
+
+    # Setup the base dir
+    td = tmpdir.join("test.py")
+    td.write("#!/bin/env python")
+    expected_sources.append(str(td))
+
+    # Make some more directories, each with a file present
+    for d in ["foo", "bar", "buzz"]:
+        dd = tmpdir.mkdir(d)
+        dummy_file = dd.join("test.py")
+        dummy_file.write("#!/bin/env python")
+        expected_sources.append(str(dummy_file))
+
+    # Get the flattened version of the base directory
+    flattened = p._flatten_sources(sources)
+
+    # Make sure that the lists are the same
+    assert sorted(expected_sources) == sorted(flattened)