Remove software carpentries logo

[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 f7e037a..25388d3
--- a/bin/lesson_check.py
+++ b/bin/lesson_check.py
@@ -1,5 +1,3 @@
-#!/usr/bin/env python
-
 """
 Check lesson files and their contents.
 """
@@ -61,6 +59,7 @@ P_INTERNAL_INCLUDE_LINK = re.compile(r'^{% include ([^ ]*) %}$')
 # What kinds of blockquotes are allowed?
 KNOWN_BLOCKQUOTES = {
     'callout',
+    'caution',
     'challenge',
     'checklist',
     'discussion',
@@ -69,22 +68,17 @@ KNOWN_BLOCKQUOTES = {
     'prereq',
     'quotation',
     'solution',
-    'testimonial'
+    'testimonial',
+    'warning'
 }
 
 # What kinds of code fragments are allowed?
+# Below we allow all 'language-*' code blocks
 KNOWN_CODEBLOCKS = {
     'error',
     'output',
     'source',
-    'language-bash',
-    'html',
-    'language-make',
-    'language-matlab',
-    'language-python',
-    'language-r',
-    'language-shell',
-    'language-sql'
+    'warning'
 }
 
 # What fields are required in teaching episode metadata?
@@ -114,9 +108,13 @@ def main():
 
     args = parse_args()
     args.reporter = Reporter()
-    check_config(args.reporter, args.source_dir)
+    life_cycle = check_config(args.reporter, args.source_dir)
+    # pre-alpha lessons should report without error
+    if life_cycle == "pre-alpha":
+        args.permissive = True
     check_source_rmd(args.reporter, args.source_dir, args.parser)
     args.references = read_references(args.reporter, args.reference_path)
+
     docs = read_all_markdown(args.source_dir, args.parser)
     check_fileset(args.source_dir, args.reporter, list(docs.keys()))
     check_unwanted_files(args.source_dir, args.reporter)
@@ -156,7 +154,7 @@ def parse_args():
                         dest='trailing_whitespace',
                         help='Check for trailing whitespace')
     parser.add_argument('--permissive',
-                        default=True,
+                        default=False,
                         action="store_true",
                         dest='permissive',
                         help='Do not raise an error even if issues are detected')
@@ -178,7 +176,7 @@ def check_config(reporter, source_dir):
     reporter.check_field(config_file, 'configuration',
                          config, 'kind', 'lesson')
     reporter.check_field(config_file, 'configuration',
-                         config, 'carpentry', ('swc', 'dc', 'lc', 'cp'))
+                         config, 'carpentry', ('swc', 'dc', 'lc', 'cp', 'incubator'))
     reporter.check_field(config_file, 'configuration', config, 'title')
     reporter.check_field(config_file, 'configuration', config, 'email')
 
@@ -190,6 +188,7 @@ def check_config(reporter, source_dir):
         reporter.check(defaults in config.get('defaults', []),
                    'configuration',
                    '"root" not set to "." in configuration')
+    return config['life_cycle']
 
 def check_source_rmd(reporter, source_dir, parser):
     """Check that Rmd episode files include `source: Rmd`"""
@@ -216,7 +215,7 @@ 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
@@ -256,31 +255,15 @@ def read_all_markdown(source_dir, parser):
     {path : {'metadata':yaml, 'metadata_len':N, 'text':text, 'lines':[(i, line, len)], 'doc':doc}}
     """
 
-    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):
-            data = read_markdown(parser, filename)
-            if data:
-                result[filename] = data
-
-    return result
-
     all_dirs = [os.path.join(source_dir, d) for d in SOURCE_DIRS]
-    print(all_dirs)
     all_patterns = [os.path.join(d, '*.md') for d in all_dirs]
-    print(all_patterns)
     result = {}
     for pat in all_patterns:
-        print(pat)
         for filename in glob.glob(pat):
             data = read_markdown(parser, filename)
             if data:
-                print(filename)
                 result[filename] = data
-#    return result
+    return result
 
 
 def check_fileset(source_dir, reporter, filenames_present):
@@ -294,18 +277,18 @@ def check_fileset(source_dir, reporter, filenames_present):
 
     # Check episode files' names.
     seen = []
-    for filepath in filenames_present:
-        if '_episodes' not in filepath:
+    for filename in filenames_present:
+        if '_episodes' not in filename:
             continue
 
         # split path to check episode name
-        fname = os.path.basename(filepath)
-        m = P_EPISODE_FILENAME.search(fname)
+        base_name = os.path.basename(filename)
+        m = P_EPISODE_FILENAME.search(base_name)
         if m and m.group(1):
             seen.append(m.group(1))
         else:
             reporter.add(
-                None, 'Episode {0} has badly-formatted filename', filepath)
+                None, 'Episode {0} has badly-formatted filename', filename)
 
     # Check for duplicate episode numbers.
     reporter.check(len(seen) == len(set(seen)),
@@ -407,7 +390,7 @@ class CheckBase:
 
         for node in self.find_all(self.doc, {'type': 'codeblock'}):
             cls = self.get_val(node, 'attr', 'class')
-            self.reporter.check(cls in KNOWN_CODEBLOCKS,
+            self.reporter.check(cls in KNOWN_CODEBLOCKS or cls.startswith('language-'),
                                 (self.filename, self.get_loc(node)),
                                 'Unknown or missing code block type {0}',
                                 cls)
@@ -574,7 +557,7 @@ 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)
 ]