def parse_folder(path):
"""
Parses all .bib files in given folder.
Returns a tuple (parsed_iten, search_index) containing all items found
"""
if not os.path.isdir(path):
raise Exception("Path to folder expected")
parsed_items = []
files = utils.search_in_folder(path, lambda path: path.endswith(".bib"))
executor = concurrent.futures.ProcessPoolExecutor(max_workers=multiprocessing.cpu_count())
futures = [
executor.submit(
BibParser()._parse_file,
os.path.join(path, filename)
)
for filename in files
]
for future in futures:
parsed_items += future.result()
executor.shutdown()
parsed_items = list(sorted(
parsed_items,
key=BibItem.key_to_key_func(const.DEFAULT_ORDER_BY)
))
item_index = search_index.Index(parsed_items)
fin_ctx = FinalizingContext(item_index)
for item in parsed_items:
item.finalize_item_set(fin_ctx)
item_index.update(parsed_items)
return (parsed_items, item_index)
def parse_folder(path):
"""
Parses all .bib files in given folder.
Returns a tuple (parsed_iten, search_index) containing all items found
"""
if not os.path.isdir(path):
raise Exception("Path to folder expected")
parsed_items = []
files = utils.search_in_folder(path, lambda path: path.endswith(".bib"))
executor = concurrent.futures.ProcessPoolExecutor(max_workers=multiprocessing.cpu_count())
futures = [
executor.submit(
BibParser()._parse_file,
os.path.join(path, filename)
)
for filename in files
]
for future in futures:
parsed_items += future.result()
executor.shutdown()
parsed_items = list(sorted(
parsed_items,
key=BibItem.key_to_key_func(const.DEFAULT_ORDER_BY)
))
item_index = search_index.Index(parsed_items)
fin_ctx = FinalizingContext(item_index)
for item in parsed_items:
item.finalize_item_set(fin_ctx)
item_index.update(parsed_items)
return (parsed_items, item_index)
def fetch_filelist_from_fs():
EXCLUDED_FOLDERS = {
"Ancillary sources (not in bibliography)",
"Leaflets (not in bibliography)"
}
trim_root = lambda path: "/" + os.path.relpath(path, start=config.www.elibrary_dir)
filter = lambda path: os.path.isfile(path) and path.endswith(".pdf")
return set(map(
trim_root,
utils.search_in_folder(config.www.elibrary_dir, filter, excludes=EXCLUDED_FOLDERS)
))
def fetch_filelist_from_fs():
EXCLUDED_FOLDERS = {
"Ancillary sources (not in bibliography)",
"Leaflets (not in bibliography)"
}
trim_root = lambda path: "/" + os.path.relpath(path, start=config.www.elibrary_dir)
filter = lambda path: os.path.isfile(path) and path.endswith(".pdf")
return set(map(
trim_root,
utils.search_in_folder(config.www.elibrary_dir, filter, excludes=EXCLUDED_FOLDERS)
))
def fetch_added_on_from_git():
BLAME_REGEXP = re.compile(
#commit hash
r"^[\^0-9a-z]+\s+"
#filename
r"[^\s]*?\s+"
#committer's name
r"\([A-Za-z\-\s\\]*?\s+"
#commit date
r"(?P<date>\d{4}-\d{2}-\d{2})\s+"
#commit time
r"[\d:]+\s+"
#commit time zone
r"[+\d]+\s+"
#line numberq
r"\d+\)\s+"
#item id
r"(?P<id>[a-z_\d]+),\s*$"
)
def blame_file(path):
data = subprocess.check_output([
"git",
"blame",
#WARN: using show-name to guarantee output format
"--show-name",
#no such option in "git blame" on trusty
#"--no-progress",
path
]).decode()
result = dict()
for line in data.split("\n"):
match = BLAME_REGEXP.search(line)
if not match:
continue
item_id = match.group("id")
date = datetime.datetime.strptime(
match.group("date"),
config.parser.date_format
)
result[item_id] = date
return result
result = dict()
filter = lambda path: path.endswith(".bib")
for path in utils.search_in_folder(config.parser.bibdata_dir, filter):
result.update(blame_file(path))
return result
def fetch_added_on_from_git():
BLAME_REGEXP = re.compile(
#commit hash
r"^[\^0-9a-z]+\s+"
#filename
r"[^\s]*?\s+"
#committer's name
r"\([A-Za-z\-\s\\]*?\s+"
#commit date
r"(?P<date>\d{4}-\d{2}-\d{2})\s+"
#commit time
r"[\d:]+\s+"
#commit time zone
r"[+\d]+\s+"
#line numberq
r"\d+\)\s+"
#item id
r"(?P<id>[a-z_\d]+),\s*$"
)
def blame_file(path):
data = subprocess.check_output([
"git",
"blame",
#WARN: using show-name to guarantee output format
"--show-name",
#no such option in "git blame" on trusty
#"--no-progress",
path
]).decode()
result = dict()
for line in data.split("\n"):
match = BLAME_REGEXP.search(line)
if not match:
continue
item_id = match.group("id")
date = datetime.datetime.strptime(
match.group("date"),
config.parser.date_format
)
result[item_id] = date
return result
result = dict()
filter = lambda path: path.endswith(".bib")
for path in utils.search_in_folder(config.parser.bibdata_dir, filter):
result.update(blame_file(path))
return result
def fetch_backups_from_fs():
if not os.path.isdir(config.www.backup_dir):
return []
EXCLUDED_FOLDERS = {
"Cooking", "Fashion", "Leaflets (not in bibliography)", "Postcards",
"Useless"
}
trim_root = lambda path: "/" + os.path.relpath(path,
start=config.www.backup_dir)
filter = lambda path: (os.path.isdir(path) and const.FILENAME_REGEXP.match(
os.path.basename(path)))
return set(
map(
trim_root,
utils.search_in_folder(config.www.backup_dir,
filter,
excludes=EXCLUDED_FOLDERS)))
def fetch_backups_from_fs():
if not os.path.isdir(config.www.backup_dir):
return []
EXCLUDED_FOLDERS = {
"Cooking",
"Fashion",
"Leaflets (not in bibliography)",
"Postcards",
"Useless"
}
trim_root = lambda path: "/" + os.path.relpath(path, start=config.www.backup_dir)
filter = lambda path: (
os.path.isdir(path) and
const.FILENAME_REGEXP.match(os.path.basename(path))
)
return set(map(
trim_root,
utils.search_in_folder(config.www.backup_dir, filter, excludes=EXCLUDED_FOLDERS)
))
def fetch_backups_from_fs():
if not os.path.isdir(config.www.backup_dir):
return []
FOLDERS_TO_VALIDATE = {
"Cooking",
"Fashion",
"Library",
}
trim_root = lambda path: os.path.relpath(path, start=config.www.backup_dir)
filter = lambda path: (
os.path.isdir(path) and
const.FILENAME_REGEXP.match(os.path.basename(path))
)
backups = []
for basename in FOLDERS_TO_VALIDATE:
folder = os.path.join(config.www.backup_dir, basename)
backups += list(
map(
trim_root,
utils.search_in_folder(folder, filter)
)
)
return backups