X-Git-Url: https://git.arvados.org/rnaseq-cwl-training.git/blobdiff_plain/c2f89a7a8d78a71070e91ac3a2b6e5a99095e8b3..7f8e13d704e49b625b25b7b655d4c21db70c7ccf:/bin/lesson_check.py diff --git a/bin/lesson_check.py b/bin/lesson_check.py index c85661e..311687e 100755 --- a/bin/lesson_check.py +++ b/bin/lesson_check.py @@ -4,6 +4,7 @@ Check lesson files and their contents. """ +from __future__ import print_function import sys import os import glob @@ -11,7 +12,7 @@ import json import re from optparse import OptionParser -from util import Reporter, read_markdown, load_yaml +from util import Reporter, read_markdown, load_yaml, check_unwanted_files, require, IMAGE_FILE_SUFFIX __version__ = '0.2' @@ -40,6 +41,15 @@ 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_INTERNALLY_DEFINED_LINK = re.compile(r'\[[^\]]+\]\[[^\]]+\]') + # What kinds of blockquotes are allowed? KNOWN_BLOCKQUOTES = { 'callout', @@ -61,6 +71,7 @@ KNOWN_CODEBLOCKS = { 'source', 'bash', 'make', + 'matlab', 'python', 'r', 'sql' @@ -94,9 +105,11 @@ def main(): check_config(args.reporter, args.source_dir) 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() @@ -106,6 +119,7 @@ def parse_args(): parser = OptionParser() parser.add_option('-l', '--linelen', default=False, + action="store_true", dest='line_lengths', help='Check line lengths') parser.add_option('-p', '--parser', @@ -118,6 +132,7 @@ def parse_args(): help='source directory') parser.add_option('-w', '--whitespace', default=False, + action="store_true", dest='trailing_whitespace', help='Check for trailing whitespace') @@ -136,6 +151,13 @@ def check_config(reporter, source_dir): config_file = os.path.join(source_dir, '_config.yml') config = load_yaml(config_file) reporter.check_field(config_file, 'configuration', config, 'kind', 'lesson') + reporter.check_field(config_file, 'configuration', config, 'carpentry', ('swc', 'dc')) + 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_all_markdown(source_dir, parser): @@ -192,6 +214,38 @@ 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.""" @@ -200,14 +254,6 @@ 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.""" @@ -235,6 +281,7 @@ class CheckBase(object): self.check_trailing_whitespace() self.check_blockquote_classes() self.check_codeblock_classes() + self.check_defined_link_references() def check_metadata(self): @@ -263,11 +310,11 @@ class CheckBase(object): """Check for whitespace at the ends of lines.""" if self.args.trailing_whitespace: - trailing = [i for (i, l, n) in self.lines if l.endswidth(' ')] + 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 over])) + ', '.join([str(i) for i in trailing])) def check_blockquote_classes(self): @@ -292,6 +339,26 @@ 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]. If + the label contains '{{...}}', it is hopefully a references to + a configuration value - we should check that, but don't right + now. + """ + + result = set() + for node in self.find_all(self.doc, {'type' : 'text'}): + for match in P_INTERNALLY_DEFINED_LINK.findall(node['value']): + if '{{' not in match: + result.add(match) + 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.""" @@ -361,6 +428,12 @@ 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."""