add three more common languages (#497)

[rnaseq-cwl-training.git] / bin / lesson_check.py

diff --git a/bin/lesson_check.py b/bin/lesson_check.py
old mode 100755 (executable)
new mode 100644 (file)
index 7d135dc..618f322
--- a/bin/lesson_check.py
+++ b/bin/lesson_check.py
@@ -77,6 +77,9 @@ KNOWN_CODEBLOCKS = {
     'source',
     'language-bash',
     'html',
+    'language-c',
+    'language-cmake',
+    'language-cpp',
     'language-make',
     'language-matlab',
     'language-python',
@@ -215,7 +218,7 @@ def read_references(reporter, ref_path):
     result = {}
     urls_seen = set()
 
-    with open(ref_path, 'r') as reader:
+    with open(ref_path, 'r', encoding='utf-8') as reader:
         for (num, line) in enumerate(reader, 1):
 
             if P_INTERNAL_INCLUDE_LINK.search(line): continue
@@ -255,16 +258,14 @@ def read_all_markdown(source_dir, parser):
     {path : {'metadata':yaml, 'metadata_len':N, 'text':text, 'lines':[(i, line, len)], 'doc':doc}}
     """
 
+    all_dirs = [os.path.join(source_dir, d) for d in SOURCE_DIRS]
+    all_patterns = [os.path.join(d, '*.md') for d in all_dirs]
     result = {}
-    for d in SOURCE_DIRS:
-        dpath = os.path.join(source_dir, d)
-
-        pattern = os.path.join(dpath, '*.md')
-        for filename in glob.glob(pattern):
+    for pat in all_patterns:
+        for filename in glob.glob(pat):
             data = read_markdown(parser, filename)
             if data:
                 result[filename] = data
-
     return result
 
 
@@ -559,7 +560,7 @@ CHECKERS = [
     (re.compile(r'README\.md'), CheckNonJekyll),
     (re.compile(r'index\.md'), CheckIndex),
     (re.compile(r'reference\.md'), CheckReference),
-    (re.compile(r'_episodes/.*\.md'), CheckEpisode),
+    (re.compile(os.path.join('_episodes', '*\.md')), CheckEpisode),
     (re.compile(r'.*\.md'), CheckGeneric)
 ]