lordwelch/comicapi
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'volume' into develop

Browse Source
This commit is contained in:
lordwelch 2022-05-24 11:30:15 -07:00
commit 1c39165fcc
1 changed files with 25 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
comicapi/filenameparser.py
View File

@ -38,6 +38,8 @@ logger = logging.getLogger(__name__)
class FileNameParser: class FileNameParser:
volume_regex = r"v(?:|ol|olume)\.?\s?"
def __init__(self) -> None: def __init__(self) -> None:
self.series = "" self.series = ""
self.volume = "" self.volume = ""
@ -117,6 +119,11 @@ class FileNameParser:
# we should now have a cleaned up filename version with all the words in # we should now have a cleaned up filename version with all the words in
# the same positions as original filename # the same positions as original filename
# search for volume number
match = re.search(self.volume_regex + r"(\d+)", filename, re.IGNORECASE)
if match:
self.volume = match.group(1)
# make a list of each word and its position # make a list of each word and its position
word_list = [] word_list = []
for m in re.finditer(r"\S+", filename): for m in re.finditer(r"\S+", filename):
@ -194,10 +201,12 @@ class FileNameParser:
series = re.sub(r"\(.*?\)", "", series) series = re.sub(r"\(.*?\)", "", series)
# search for volume number # search for volume number
match = re.search(r"(.+)([vV]|[Vv][oO][Ll]\.?\s?)(\d+)\s*$", series) match = re.search(r"(.+)" + self.volume_regex + r"(\d+)", series, re.IGNORECASE)
if match: if match:
series = match.group(1) series = match.group(1)
volume = match.group(3) volume = match.group(2)
if self.volume:
volume = self.volume
# if a volume wasn't found, see if the last word is a year in parentheses # if a volume wasn't found, see if the last word is a year in parentheses
# since that's a common way to designate the volume # since that's a common way to designate the volume
@ -221,6 +230,9 @@ class FileNameParser:
except: except:
pass pass
if volume:
series = re.sub(r"\s+v(|ol|olume)$", "", series)
return series, volume.strip() return series, volume.strip()
def get_year(self, filename: str, issue_end: int) -> str: def get_year(self, filename: str, issue_end: int) -> str:
@ -250,7 +262,7 @@ class FileNameParser:
remainder = self.fix_spaces(remainder, remove_dashes=False) remainder = self.fix_spaces(remainder, remove_dashes=False)
if volume != "": if volume != "":
remainder = remainder.replace("Vol." + volume, "", 1) remainder = re.sub(r"(?i)(.+)((?:v(?:|ol|olume))\.?\s?)" + volume, "", remainder, count=1)
if year != "": if year != "":
remainder = remainder.replace(year, "", 1) remainder = remainder.replace(year, "", 1)
if count != "": if count != "":
@ -282,6 +294,9 @@ class FileNameParser:
self.issue, issue_start, issue_end = self.get_issue_number(filename) self.issue, issue_start, issue_end = self.get_issue_number(filename)
self.series, self.volume = self.get_series_name(filename, issue_start) self.series, self.volume = self.get_series_name(filename, issue_start)
if self.issue == "":
self.issue = self.volume
# provides proper value when the filename doesn't have a issue number # provides proper value when the filename doesn't have a issue number
if issue_end == 0: if issue_end == 0:
issue_end = len(self.series) issue_end = len(self.series)
@ -290,13 +305,11 @@ class FileNameParser:
self.issue_count = self.get_issue_count(filename, issue_end) self.issue_count = self.get_issue_count(filename, issue_end)
self.remainder = self.get_remainder(filename, self.year, self.issue_count, self.volume, issue_end) self.remainder = self.get_remainder(filename, self.year, self.issue_count, self.volume, issue_end)
if self.volume != "":
self.volume = issuestring.IssueString(self.volume).as_string()
if self.issue != "": if self.issue != "":
# strip off leading zeros self.issue = issuestring.IssueString(self.issue).as_string()
self.issue = self.issue.lstrip("0") print(self.issue, self.volume)
if self.issue == "":
self.issue = "0"
if self.issue[0] == ".":
self.issue = "0" + self.issue
class FilenameInfo(TypedDict, total=False): class FilenameInfo(TypedDict, total=False):
@ -892,12 +905,9 @@ def parse_finish(p: Parser) -> Optional[Callable[[Parser], Optional[Callable]]]:
if "alternate" in p.filename_info: if "alternate" in p.filename_info:
p.filename_info["issue"] = p.filename_info["alternate"] p.filename_info["issue"] = p.filename_info["alternate"]
p.filename_info["alternate"] = "" p.filename_info["alternate"] = ""
else:
# TODO: This never happens if "volume" in p.filename_info:
inp = [x for x in p.input if x not in p.irrelevant and x not in p.used_items and x.typ != eof.typ] p.filename_info["issue"] = p.filename_info["volume"]
if len(inp) == 1 and inp[0].typ == filenamelexer.ItemType.Number:
p.filename_info["issue"] = inp[0].val
p.used_items.append(inp[0])
remove_items = [] remove_items = []
if p.remove_fcbd: if p.remove_fcbd: