Check lesson files and their contents.
"""
-from __future__ import print_function
-import sys
+
import os
import glob
-import json
import re
from optparse import OptionParser
-from util import Reporter, read_markdown, load_yaml, check_unwanted_files, require, IMAGE_FILE_SUFFIX
+from util import (Reporter, read_markdown, load_yaml, check_unwanted_files,
+ require)
__version__ = '0.3'
# FIXME: We do not yet validate whether any files have the required
# YAML headers, but should in the future.
# The '%' is replaced with the source directory path for checking.
-# Episodes are handled specially, and extra files in '_extras' are also handled specially.
-# This list must include all the Markdown files listed in the 'bin/initialize' script.
+# Episodes are handled specially, and extra files in '_extras' are also handled
+# specially. This list must include all the Markdown files listed in the
+# 'bin/initialize' script.
REQUIRED_FILES = {
'%/CONDUCT.md': True,
'%/CONTRIBUTING.md': False,
# How long are lines allowed to be?
MAX_LINE_LEN = 100
+
def main():
"""Main driver."""
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_fileset(args.source_dir, args.reporter, list(docs.keys()))
check_unwanted_files(args.source_dir, args.reporter)
- for filename in docs.keys():
+ for filename in list(docs.keys()):
checker = create_checker(args, filename, docs[filename])
checker.check()
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', 'lc'))
+ 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')
if m and m.group(1):
seen.append(m.group(1))
else:
- reporter.add(None, 'Episode {0} has badly-formatted filename', filename)
+ reporter.add(
+ None, 'Episode {0} has badly-formatted filename', filename)
# Check for duplicate episode numbers.
reporter.check(len(seen) == len(set(seen)),
- None,
- 'Duplicate episode numbers {0} vs {1}',
- sorted(seen), sorted(set(seen)))
+ None,
+ 'Duplicate episode numbers {0} vs {1}',
+ sorted(seen), sorted(set(seen)))
# Check that numbers are consecutive.
- seen = [int(s) for s in seen]
- seen.sort()
+ seen = sorted([int(s) for s in seen])
clean = True
for i in range(len(seen) - 1):
clean = clean and ((seen[i+1] - seen[i]) == 1)
super(CheckBase, self).__init__()
self.args = args
- self.reporter = self.args.reporter # for convenience
+ self.reporter = self.args.reporter # for convenience
self.filename = filename
self.metadata = metadata
self.metadata_len = metadata_len
self.layout = None
-
def check(self):
"""Run tests."""
self.check_codeblock_classes()
self.check_defined_link_references()
-
def check_metadata(self):
"""Check the YAML metadata."""
'Missing metadata entirely')
if self.metadata and (self.layout is not None):
- self.reporter.check_field(self.filename, 'metadata', self.metadata, 'layout', self.layout)
-
+ self.reporter.check_field(
+ self.filename, 'metadata', self.metadata, 'layout', self.layout)
def check_line_lengths(self):
"""Check the raw text of the lesson body."""
if self.args.line_lengths:
- over = [i for (i, l, n) in self.lines if (n > MAX_LINE_LEN) and (not l.startswith('!'))]
+ 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,
'Line(s) are too long: {0}',
', '.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)]
+ 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."""
- for node in self.find_all(self.doc, {'type' : 'blockquote'}):
+ for node in self.find_all(self.doc, {'type': 'blockquote'}):
cls = self.get_val(node, 'attr', 'class')
self.reporter.check(cls in KNOWN_BLOCKQUOTES,
(self.filename, self.get_loc(node)),
'Unknown or missing blockquote type {0}',
cls)
-
def check_codeblock_classes(self):
"""Check that all code blocks have known classes."""
- for node in self.find_all(self.doc, {'type' : 'codeblock'}):
+ 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.filename, self.get_loc(node)),
'Unknown or missing code block type {0}',
cls)
-
def check_defined_link_references(self):
"""Check that defined links resolve in the file.
"""
result = set()
- for node in self.find_all(self.doc, {'type' : 'text'}):
+ 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]
'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."""
- assert type(pattern) == dict, 'Patterns must be dictionaries'
+ assert isinstance(pattern, dict), 'Patterns must be dictionaries'
if accum is None:
accum = []
if self.match(node, pattern):
self.find_all(child, pattern, accum)
return accum
-
def match(self, node, pattern):
"""Does this node match the given pattern?"""
if key not in node:
return False
val = pattern[key]
- if type(val) == str:
+ if isinstance(val, str):
if node[key] != val:
return False
- elif type(val) == dict:
+ elif isinstance(val, dict):
if not self.match(node[key], val):
return False
return True
-
def get_val(self, node, *chain):
"""Get value one or more levels down."""
break
return curr
-
def get_loc(self, node):
"""Convenience method to get node's line number."""
"""Check a file that isn't translated by Jekyll."""
def __init__(self, args, filename, metadata, metadata_len, text, lines, doc):
- super(CheckNonJekyll, self).__init__(args, filename, metadata, metadata_len, text, lines, doc)
-
+ super(CheckNonJekyll, self).__init__(
+ args, filename, metadata, metadata_len, text, lines, doc)
def check_metadata(self):
self.reporter.check(self.metadata is None,
"""Check the main index page."""
def __init__(self, args, filename, metadata, metadata_len, text, lines, doc):
- super(CheckIndex, self).__init__(args, filename, metadata, metadata_len, text, lines, doc)
+ super(CheckIndex, self).__init__(args, filename,
+ metadata, metadata_len, text, lines, doc)
self.layout = 'lesson'
def check_metadata(self):
"""Check an episode page."""
def __init__(self, args, filename, metadata, metadata_len, text, lines, doc):
- super(CheckEpisode, self).__init__(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:
else:
self.check_metadata_fields(TEACHING_METADATA_FIELDS)
-
def check_metadata_fields(self, expected):
for (name, type_) in expected:
if name not in self.metadata:
self.reporter.add(self.filename,
'Missing metadata field {0}',
name)
- elif type(self.metadata[name]) != type_:
+ elif not isinstance(self.metadata[name], type_):
self.reporter.add(self.filename,
'"{0}" has wrong type in metadata ({1} instead of {2})',
name, type(self.metadata[name]), type_)
-
def check_reference_inclusion(self):
"""Check that links file has been included."""
"""Check the reference page."""
def __init__(self, args, filename, metadata, metadata_len, text, lines, doc):
- super(CheckReference, self).__init__(args, filename, metadata, metadata_len, text, lines, doc)
+ super(CheckReference, self).__init__(
+ args, filename, metadata, metadata_len, text, lines, doc)
self.layout = 'reference'
"""Check a generic page."""
def __init__(self, args, filename, metadata, metadata_len, text, lines, doc):
- super(CheckGeneric, self).__init__(args, filename, metadata, metadata_len, text, lines, doc)
+ super(CheckGeneric, self).__init__(args, filename,
+ metadata, metadata_len, text, lines, doc)
self.layout = 'page'
Check repository settings.
"""
-from __future__ import print_function
+
import sys
import os
from subprocess import Popen, PIPE
import re
from optparse import OptionParser
-from util import Reporter, load_yaml, require
+from util import Reporter, require
# Import this way to produce a more useful error message.
try:
# Expected labels and colors.
EXPECTED = {
- 'help wanted' : 'dcecc7',
- 'status:in progress' : '9bcc65',
- 'status:changes requested' : '679f38',
- 'status:wait' : 'fff2df',
- 'status:refer to cac' : 'ffdfb2',
- 'status:need more info' : 'ee6c00',
- 'status:blocked' : 'e55100',
- 'status:out of scope' : 'eeeeee',
- 'status:duplicate' : 'bdbdbd',
- 'type:typo text' : 'f8bad0',
- 'type:bug' : 'eb3f79',
- 'type:formatting' : 'ac1357',
- 'type:template and tools' : '7985cb',
- 'type:instructor guide' : '00887a',
- 'type:discussion' : 'b2e5fc',
- 'type:enhancement' : '7fdeea',
- 'type:clarification' : '00acc0',
- 'type:teaching example' : 'ced8dc',
- 'good first issue' : 'ffeb3a',
- 'high priority' : 'd22e2e'
+ 'help wanted': 'dcecc7',
+ 'status:in progress': '9bcc65',
+ 'status:changes requested': '679f38',
+ 'status:wait': 'fff2df',
+ 'status:refer to cac': 'ffdfb2',
+ 'status:need more info': 'ee6c00',
+ 'status:blocked': 'e55100',
+ 'status:out of scope': 'eeeeee',
+ 'status:duplicate': 'bdbdbd',
+ 'type:typo text': 'f8bad0',
+ 'type:bug': 'eb3f79',
+ 'type:formatting': 'ac1357',
+ 'type:template and tools': '7985cb',
+ 'type:instructor guide': '00887a',
+ 'type:discussion': 'b2e5fc',
+ 'type:enhancement': '7fdeea',
+ 'type:clarification': '00acc0',
+ 'type:teaching example': 'ced8dc',
+ 'good first issue': 'ffeb3a',
+ 'high priority': 'd22e2e'
}
# Guess.
cmd = 'git remote -v'
- p = Popen(cmd, shell=True, stdin=PIPE, stdout=PIPE, close_fds=True, universal_newlines=True)
+ p = Popen(cmd, shell=True, stdin=PIPE, stdout=PIPE,
+ close_fds=True, universal_newlines=True)
stdout_data, stderr_data = p.communicate()
stdout_data = stdout_data.split('\n')
matches = [P_GIT_REMOTE.match(line) for line in stdout_data]
'Unexpected output from git remote command: "{0}"'.format(matches))
username = matches[0].group(1)
- require(username, 'empty username in git remote output {0}'.format(matches[0]))
+ require(
+ username, 'empty username in git remote output {0}'.format(matches[0]))
project_name = matches[0].group(2)
- require(username, 'empty project name in git remote output {0}'.format(matches[0]))
+ require(
+ username, 'empty project name in git remote output {0}'.format(matches[0]))
url = F_REPO_URL.format(username, project_name)
return url
"""
m = P_REPO_URL.match(repo_url)
- require(m, 'repository URL {0} does not match expected pattern'.format(repo_url))
+ require(
+ m, 'repository URL {0} does not match expected pattern'.format(repo_url))
username = m.group(1)
require(username, 'empty username in repository URL {0}'.format(repo_url))
project_name = m.group(2)
- require(username, 'empty project name in repository URL {0}'.format(repo_url))
+ require(
+ username, 'empty project name in repository URL {0}'.format(repo_url))
url = F_API_URL.format(username, project_name)
r = requests.get(url)
-from __future__ import print_function
+
import sys
import os
import json
# (Can't use 'None' because that might be a legitimate value.)
REPORTER_NOT_SET = []
+
class Reporter(object):
"""Collect and report errors."""
super(Reporter, self).__init__()
self.messages = []
-
def check_field(self, filename, name, values, key, expected=REPORTER_NOT_SET):
"""Check that a dictionary has an expected value."""
pass
elif type(expected) in (tuple, set, list):
if values[key] not in expected:
- self.add(filename, '{0} {1} value {2} is not in {3}', name, key, values[key], expected)
+ self.add(
+ filename, '{0} {1} value {2} is not in {3}', name, key, values[key], expected)
elif values[key] != expected:
- self.add(filename, '{0} {1} is {2} not {3}', name, key, values[key], expected)
-
+ self.add(filename, '{0} {1} is {2} not {3}',
+ name, key, values[key], expected)
def check(self, condition, location, fmt, *args):
"""Append error if condition not met."""
if not condition:
self.add(location, fmt, *args)
-
def add(self, location, fmt, *args):
"""Append error unilaterally."""
self.messages.append((location, fmt.format(*args)))
-
def report(self, stream=sys.stdout):
"""Report all messages in order."""
# Split into lines.
metadata_len = 0 if metadata_raw is None else metadata_raw.count('\n')
- lines = [(metadata_len+i+1, line, len(line)) for (i, line) in enumerate(body.split('\n'))]
+ lines = [(metadata_len+i+1, line, len(line))
+ for (i, line) in enumerate(body.split('\n'))]
# Parse Markdown.
cmd = 'ruby {0}'.format(parser)
- p = Popen(cmd, shell=True, stdin=PIPE, stdout=PIPE, close_fds=True, universal_newlines=True)
+ p = Popen(cmd, shell=True, stdin=PIPE, stdout=PIPE,
+ close_fds=True, universal_newlines=True)
stdout_data, stderr_data = p.communicate(body)
doc = json.loads(stdout_data)
metadata_raw = None
metadata_yaml = None
- metadata_len = None
pieces = text.split('---', 2)
if len(pieces) == 3:
try:
metadata_yaml = yaml.load(metadata_raw)
except yaml.YAMLError as e:
- print('Unable to parse YAML header in {0}:\n{1}'.format(path, e), file=sys.stderr)
+ print('Unable to parse YAML header in {0}:\n{1}'.format(
+ path, e), file=sys.stderr)
sys.exit(1)
return metadata_raw, metadata_yaml, text
with open(filename, 'r') as reader:
return yaml.load(reader)
except (yaml.YAMLError, IOError) as e:
- print('Unable to load YAML file {0}:\n{1}'.format(filename, e), file=sys.stderr)
+ print('Unable to load YAML file {0}:\n{1}'.format(
+ filename, e), file=sys.stderr)
sys.exit(1)
projects / rnaseq-cwl-training.git / commitdiff