X-Git-Url: https://git.arvados.org/rnaseq-cwl-training.git/blobdiff_plain/ac67ebc4a0303b28baf941ccf7cd465a8fecf970..78d37164c9d0a66cfbc2c524468b7f76b3c3c7b4:/bin/lesson_check.py diff --git a/bin/lesson_check.py b/bin/lesson_check.py index b65946a..f9429a1 100755 --- a/bin/lesson_check.py +++ b/bin/lesson_check.py @@ -4,17 +4,17 @@ Check lesson files and their contents. """ +from __future__ import print_function import sys import os import glob import json -import yaml import re from optparse import OptionParser -from util import Reporter, read_markdown +from util import Reporter, read_markdown, load_yaml, check_unwanted_files, require, IMAGE_FILE_SUFFIX -__version__ = '0.2' +__version__ = '0.3' # Where to look for source Markdown files. SOURCE_DIRS = ['', '_episodes', '_extras'] @@ -27,6 +27,7 @@ SOURCE_DIRS = ['', '_episodes', '_extras'] # This list must include all the Markdown files listed in the 'bin/initialize' script. REQUIRED_FILES = { '%/CONDUCT.md': True, + '%/CONTRIBUTING.md': False, '%/LICENSE.md': True, '%/README.md': False, '%/_extras/discuss.md': True, @@ -40,6 +41,18 @@ REQUIRED_FILES = { # Episode filename pattern. P_EPISODE_FILENAME = re.compile(r'/_episodes/(\d\d)-[-\w]+.md$') +# Pattern to match lines ending with whitespace. +P_TRAILING_WHITESPACE = re.compile(r'\s+$') + +# Pattern to match figure references in HTML. +P_FIGURE_REFS = re.compile(r']+src="([^"]+)"[^>]*>') + +# Pattern to match internally-defined Markdown links. +P_INTERNAL_LINK_REF = re.compile(r'\[([^\]]+)\]\[([^\]]+)\]') + +# Pattern to match reference links (to resolve internally-defined references). +P_INTERNAL_LINK_DEF = re.compile(r'^\[([^\]]+)\]:\s*(.+)') + # What kinds of blockquotes are allowed? KNOWN_BLOCKQUOTES = { 'callout', @@ -60,9 +73,12 @@ KNOWN_CODEBLOCKS = { 'output', 'source', 'bash', + 'html', 'make', + 'matlab', 'python', 'r', + 'shell', 'sql' } @@ -92,11 +108,16 @@ def main(): args = parse_args() args.reporter = Reporter() check_config(args.reporter, args.source_dir) + 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, docs.keys()) + check_unwanted_files(args.source_dir, args.reporter) for filename in docs.keys(): checker = create_checker(args, filename, docs[filename]) checker.check() + check_figures(args.source_dir, args.reporter) + args.reporter.report() @@ -106,16 +127,26 @@ def parse_args(): parser = OptionParser() parser.add_option('-l', '--linelen', default=False, - dest='line_len', + action="store_true", + dest='line_lengths', help='Check line lengths') parser.add_option('-p', '--parser', default=None, dest='parser', help='path to Markdown parser') + parser.add_option('-r', '--references', + default=None, + dest='reference_path', + help='path to Markdown file of external references') parser.add_option('-s', '--source', default=os.curdir, dest='source_dir', help='source directory') + parser.add_option('-w', '--whitespace', + default=False, + action="store_true", + dest='trailing_whitespace', + help='Check for trailing whitespace') args, extras = parser.parse_args() require(args.parser is not None, @@ -130,9 +161,46 @@ def check_config(reporter, source_dir): """Check configuration file.""" config_file = os.path.join(source_dir, '_config.yml') - with open(config_file, 'r') as reader: - config = yaml.load(reader) + config = load_yaml(config_file) reporter.check_field(config_file, 'configuration', config, 'kind', 'lesson') + reporter.check_field(config_file, 'configuration', config, 'carpentry', ('swc', 'dc', 'lc')) + reporter.check_field(config_file, 'configuration', config, 'title') + reporter.check_field(config_file, 'configuration', config, 'email') + + reporter.check({'values': {'root': '..'}} in config.get('defaults', []), + 'configuration', + '"root" not set to ".." in configuration') + + +def read_references(reporter, ref_path): + """Read shared file of reference links, returning dictionary of valid references + {symbolic_name : URL} + """ + + result = {} + urls_seen = set() + if ref_path: + with open(ref_path, 'r') as reader: + for (num, line) in enumerate(reader): + line_num = num + 1 + m = P_INTERNAL_LINK_DEF.search(line) + require(m, + '{0}:{1} not valid reference:\n{2}'.format(ref_path, line_num, line.rstrip())) + name = m.group(1) + url = m.group(2) + require(name, + 'Empty reference at {0}:{1}'.format(ref_path, line_num)) + reporter.check(name not in result, + ref_path, + 'Duplicate reference {0} at line {1}', + name, line_num) + reporter.check(url not in urls_seen, + ref_path, + 'Duplicate definition of URL {0} at line {1}', + url, line_num) + result[name] = url + urls_seen.add(url) + return result def read_all_markdown(source_dir, parser): @@ -189,6 +257,38 @@ def check_fileset(source_dir, reporter, filenames_present): seen) +def check_figures(source_dir, reporter): + """Check that all figures are present and referenced.""" + + # Get references. + try: + all_figures_html = os.path.join(source_dir, '_includes', 'all_figures.html') + with open(all_figures_html, 'r') as reader: + text = reader.read() + figures = P_FIGURE_REFS.findall(text) + referenced = [os.path.split(f)[1] for f in figures if '/fig/' in f] + except FileNotFoundError as e: + reporter.add(all_figures_html, + 'File not found') + return + + # Get actual image files (ignore non-image files). + fig_dir_path = os.path.join(source_dir, 'fig') + actual = [f for f in os.listdir(fig_dir_path) if os.path.splitext(f)[1] in IMAGE_FILE_SUFFIX] + + # Report differences. + unexpected = set(actual) - set(referenced) + reporter.check(not unexpected, + None, + 'Unexpected image files: {0}', + ', '.join(sorted(unexpected))) + missing = set(referenced) - set(actual) + reporter.check(not missing, + None, + 'Missing image files: {0}', + ', '.join(sorted(missing))) + + def create_checker(args, filename, info): """Create appropriate checker for file.""" @@ -197,14 +297,6 @@ def create_checker(args, filename, info): return cls(args, filename, **info) -def require(condition, message): - """Fail if condition not met.""" - - if not condition: - print(message, file=sys.stderr) - sys.exit(1) - - class CheckBase(object): """Base class for checking Markdown files.""" @@ -225,12 +317,14 @@ class CheckBase(object): def check(self): - """Run tests on metadata.""" + """Run tests.""" self.check_metadata() - self.check_text() + self.check_line_lengths() + self.check_trailing_whitespace() self.check_blockquote_classes() self.check_codeblock_classes() + self.check_defined_link_references() def check_metadata(self): @@ -244,10 +338,10 @@ class CheckBase(object): self.reporter.check_field(self.filename, 'metadata', self.metadata, 'layout', self.layout) - def check_text(self): + def check_line_lengths(self): """Check the raw text of the lesson body.""" - if self.args.line_len: + if self.args.line_lengths: over = [i for (i, l, n) in self.lines if (n > MAX_LINE_LEN) and (not l.startswith('!'))] self.reporter.check(not over, self.filename, @@ -255,6 +349,17 @@ class CheckBase(object): ', '.join([str(i) for i in over])) + def check_trailing_whitespace(self): + """Check for whitespace at the ends of lines.""" + + if self.args.trailing_whitespace: + trailing = [i for (i, l, n) in self.lines if P_TRAILING_WHITESPACE.match(l)] + self.reporter.check(not trailing, + self.filename, + 'Line(s) end with whitespace: {0}', + ', '.join([str(i) for i in trailing])) + + def check_blockquote_classes(self): """Check that all blockquotes have known classes.""" @@ -277,6 +382,25 @@ class CheckBase(object): cls) + def check_defined_link_references(self): + """Check that defined links resolve in the file. + + Internally-defined links match the pattern [text][label]. + """ + + result = set() + for node in self.find_all(self.doc, {'type' : 'text'}): + for match in P_INTERNAL_LINK_REF.findall(node['value']): + text = match[0] + link = match[1] + if link not in self.args.references: + result.add('"{0}"=>"{1}"'.format(text, link)) + self.reporter.check(not result, + self.filename, + 'Internally-defined links may be missing definitions: {0}', + ', '.join(sorted(result))) + + def find_all(self, node, pattern, accum=None): """Find all matches for a pattern.""" @@ -346,6 +470,12 @@ class CheckIndex(CheckBase): super(CheckIndex, self).__init__(args, filename, metadata, metadata_len, text, lines, doc) self.layout = 'lesson' + def check_metadata(self): + super(CheckIndex, self).check_metadata() + self.reporter.check(self.metadata.get('root', '') == '.', + self.filename, + 'Root not set to "."') + class CheckEpisode(CheckBase): """Check an episode page.""" @@ -353,6 +483,14 @@ class CheckEpisode(CheckBase): def __init__(self, args, filename, metadata, metadata_len, text, lines, doc): super(CheckEpisode, self).__init__(args, filename, metadata, metadata_len, text, lines, doc) + + def check(self): + """Run extra tests.""" + + super(CheckEpisode, self).check() + self.check_reference_inclusion() + + def check_metadata(self): super(CheckEpisode, self).check_metadata() if self.metadata: @@ -379,6 +517,26 @@ class CheckEpisode(CheckBase): name, type(self.metadata[name]), type_) + def check_reference_inclusion(self): + """Check that links file has been included.""" + + if not self.args.reference_path: + return + + for (i, last_line, line_len) in reversed(self.lines): + if last_line: + break + + require(last_line, + 'No non-empty lines in {0}'.format(self.filename)) + + include_filename = os.path.split(self.args.reference_path)[-1] + if include_filename not in last_line: + self.reporter.add(self.filename, + 'episode does not include "{0}"', + include_filename) + + class CheckReference(CheckBase): """Check the reference page."""