Merge branch 'unicode_search' into develop

2022-07-13 23:16:59 -07:00 · 2022-07-13 23:16:59 -07:00 · 99030fae6b
commit 99030fae6b
parent a00891f622 947dc81c74
18 changed files with 246 additions and 191 deletions
--- a/comicapi/utils.py
+++ b/comicapi/utils.py
@ -26,6 +26,7 @@ from shutil import which  # noqa: F401
 from typing import Any, Mapping

 import pycountry
+import thefuzz.fuzz

 logger = logging.getLogger(__name__)

@ -108,6 +109,10 @@ def remove_articles(text: str) -> str:
        "the",
        "the",
        "with",
+        "ms",
+        "mrs",
+        "mr",
+        "dr",
    ]
    new_text = ""
    for word in text.split(" "):
@ -121,19 +126,41 @@ def remove_articles(text: str) -> str:

 def sanitize_title(text: str, basic: bool = False) -> str:
    # normalize unicode and convert to ascii. Does not work for everything eg ½ to 1⁄2 not 1/2
-    text = unicodedata.normalize("NFKD", text)
-    # comicvine keeps apostrophes a part of the word
-    text = text.replace("'", "")
-    text = text.replace('"', "")
-    if not basic:
-        # comicvine ignores punctuation and accents, TODO: only remove punctuation accents and similar
-        text = re.sub(r"[^A-Za-z0-9]+", " ", text)
+    text = unicodedata.normalize("NFKD", text).casefold()
+    if basic:
+        # comicvine keeps apostrophes a part of the word
+        text = text.replace("'", "")
+        text = text.replace('"', "")
+    else:
+        # comicvine ignores punctuation and accents
+        # remove all characters that are not a letter, separator (space) or number
+        # replace any "dash punctuation" with a space
+        # makes sure that batman-superman and self-proclaimed stay separate words
+        text = "".join(
+            c if not unicodedata.category(c) in ("Pd") else " "
+            for c in text
+            if unicodedata.category(c)[0] in "LZN" or unicodedata.category(c) in ("Pd")
+        )
        # remove extra space and articles and all lower case
-        text = remove_articles(text).casefold().strip()
+        text = remove_articles(text).strip()

    return text


+def titles_match(search_title: str, record_title: str, threshold: int = 90):
+    sanitized_search = sanitize_title(search_title)
+    sanitized_record = sanitize_title(record_title)
+    ratio = thefuzz.fuzz.ratio(sanitized_search, sanitized_record)
+    logger.debug(
+        "search title: %s ; record title: %s ; ratio: %d ; match threshold: %d",
+        search_title,
+        record_title,
+        ratio,
+        threshold,
+    )
+    return ratio >= threshold
+
+
 def unique_file(file_name: pathlib.Path) -> pathlib.Path:
    name = file_name.name
    counter = 1
--- a/comictaggerlib/autotagstartwindow.py
+++ b/comictaggerlib/autotagstartwindow.py
@ -17,7 +17,7 @@ from __future__ import annotations

 import logging

-from PyQt5 import QtCore, QtGui, QtWidgets, uic
+from PyQt5 import QtCore, QtWidgets, uic

 from comictaggerlib.settings import ComicTaggerSettings

@ -39,7 +39,7 @@ class AutoTagStartWindow(QtWidgets.QDialog):

        self.cbxSpecifySearchString.setChecked(False)
        self.cbxSplitWords.setChecked(False)
-        self.leNameLengthMatchTolerance.setText(str(self.settings.id_length_delta_thresh))
+        self.sbNameMatchSearchThresh.setValue(self.settings.id_series_match_identify_thresh)
        self.leSearchString.setEnabled(False)

        self.cbxSaveOnLowConfidence.setChecked(self.settings.save_on_low_confidence)
@ -50,13 +50,12 @@ class AutoTagStartWindow(QtWidgets.QDialog):
        self.cbxWaitForRateLimit.setChecked(self.settings.wait_and_retry_on_rate_limit)
        self.cbxAutoImprint.setChecked(self.settings.auto_imprint)

-        nlmt_tip = """ <html>The <b>Name Length Match Tolerance</b> is for eliminating automatic
-                search matches that are too long compared to your series name search. The higher
+        nlmt_tip = """<html>The <b>Name Match Ratio Threshold: Auto-Identify</b> is for eliminating automatic
+                search matches that are too long compared to your series name search. The lower
                it is, the more likely to have a good match, but each search will take longer and
-                use more bandwidth. Too low, and only the very closest lexical matches will be
-                explored.</html>"""
+                use more bandwidth. Too high, and only the very closest matches will be explored.</html>"""

-        self.leNameLengthMatchTolerance.setToolTip(nlmt_tip)
+        self.sbNameMatchSearchThresh.setToolTip(nlmt_tip)

        ss_tip = """<html>
            The <b>series search string</b> specifies the search string to be used for all selected archives.
@ -66,9 +65,6 @@ class AutoTagStartWindow(QtWidgets.QDialog):
        self.leSearchString.setToolTip(ss_tip)
        self.cbxSpecifySearchString.setToolTip(ss_tip)

-        validator = QtGui.QIntValidator(0, 99, self)
-        self.leNameLengthMatchTolerance.setValidator(validator)
-
        self.cbxSpecifySearchString.stateChanged.connect(self.search_string_toggle)

        self.auto_save_on_low = False
@ -78,7 +74,7 @@ class AutoTagStartWindow(QtWidgets.QDialog):
        self.remove_after_success = False
        self.wait_and_retry_on_rate_limit = False
        self.search_string = ""
-        self.name_length_match_tolerance = self.settings.id_length_delta_thresh
+        self.name_length_match_tolerance = self.settings.id_series_match_search_thresh
        self.split_words = self.cbxSplitWords.isChecked()

    def search_string_toggle(self) -> None:
@ -93,7 +89,7 @@ class AutoTagStartWindow(QtWidgets.QDialog):
        self.assume_issue_one = self.cbxAssumeIssueOne.isChecked()
        self.ignore_leading_digits_in_filename = self.cbxIgnoreLeadingDigitsInFilename.isChecked()
        self.remove_after_success = self.cbxRemoveAfterSuccess.isChecked()
-        self.name_length_match_tolerance = int(self.leNameLengthMatchTolerance.text())
+        self.name_length_match_tolerance = int(self.leNameMatchThresh.text())
        self.wait_and_retry_on_rate_limit = self.cbxWaitForRateLimit.isChecked()
        self.split_words = self.cbxSplitWords.isChecked()

--- a/comictaggerlib/cli.py
+++ b/comictaggerlib/cli.py
@ -42,7 +42,7 @@ def actual_issue_data_fetch(
 ) -> GenericMetadata:
    # now get the particular issue data
    try:
-        comic_vine = ComicVineTalker()
+        comic_vine = ComicVineTalker(settings.id_series_match_search_thresh)
        comic_vine.wait_for_rate_limit = opts.wait_on_cv_rate_limit
        cv_md = comic_vine.fetch_issue_data(match["volume_id"], match["issue_number"], settings)
    except ComicVineTalkerException:
@ -375,7 +375,7 @@ def process_file_cli(
            if opts.issue_id is not None:
                # we were given the actual ID to search with
                try:
-                    comic_vine = ComicVineTalker()
+                    comic_vine = ComicVineTalker(settings.id_series_match_search_thresh)
                    comic_vine.wait_for_rate_limit = opts.wait_on_cv_rate_limit
                    cv_md = comic_vine.fetch_issue_data_by_issue_id(opts.issue_id, settings)
                except ComicVineTalkerException:
--- a/comictaggerlib/comiccacher.py
+++ b/comictaggerlib/comiccacher.py
@ -84,7 +84,8 @@ class ComicCacher:
                + "image_url TEXT,"
                + "description TEXT,"
                + "timestamp DATE DEFAULT (datetime('now','localtime')),"
-                + "source_name TEXT NOT NULL)"
+                + "source_name TEXT NOT NULL,"
+                + "aliases TEXT)"  # Newline separated
            )

            cur.execute(
@ -96,6 +97,7 @@ class ComicCacher:
                + "start_year INT,"
                + "timestamp DATE DEFAULT (datetime('now','localtime')), "
                + "source_name TEXT NOT NULL,"
+                + "aliases TEXT,"  # Newline separated
                + "PRIMARY KEY (id, source_name))"
            )

@ -105,6 +107,7 @@ class ComicCacher:
                + "url_list TEXT,"
                + "timestamp DATE DEFAULT (datetime('now','localtime')), "
                + "source_name TEXT NOT NULL,"
+                + "aliases TEXT,"  # Newline separated
                + "PRIMARY KEY (issue_id, source_name))"
            )

@ -121,6 +124,7 @@ class ComicCacher:
                + "description TEXT,"
                + "timestamp DATE DEFAULT (datetime('now','localtime')), "
                + "source_name TEXT NOT NULL,"
+                + "aliases TEXT,"  # Newline separated
                + "PRIMARY KEY (id, source_name))"
            )

@ -153,8 +157,8 @@ class ComicCacher:

                cur.execute(
                    "INSERT INTO VolumeSearchCache "
-                    + "(source_name, search_term, id, name, start_year, publisher, count_of_issues, image_url, description) "
-                    + "VALUES(?, ?, ?, ?, ?, ?, ?, ?, ?)",
+                    + "(source_name, search_term, id, name, start_year, publisher, count_of_issues, image_url, description, aliases) "
+                    + "VALUES(?, ?, ?, ?, ?, ?, ?, ?, ?, ?)",
                    (
                        source_name,
                        search_term.casefold(),
@ -165,6 +169,7 @@ class ComicCacher:
                        record["count_of_issues"],
                        url,
                        record["description"],
+                        record["aliases"],
                    ),
                )

@ -197,6 +202,7 @@ class ComicCacher:
                        "description": record[7],
                        "publisher": {"name": record[4]},
                        "image": {"super_url": record[6]},
+                        "aliases": record[10],
                    }
                )

@ -268,6 +274,7 @@ class ComicCacher:
                "count_of_issues": cv_volume_record["count_of_issues"],
                "start_year": cv_volume_record["start_year"],
                "timestamp": timestamp,
+                "aliases": cv_volume_record["aliases"],
            }
            self.upsert(cur, "volumes", data)

@ -295,6 +302,7 @@ class ComicCacher:
                    "thumb_url": issue["image"]["thumb_url"],
                    "description": issue["description"],
                    "timestamp": timestamp,
+                    "aliases": issue["aliases"],
                }
                self.upsert(cur, "issues", data)

@ -313,7 +321,8 @@ class ComicCacher:

            # fetch
            cur.execute(
-                "SELECT source_name,id,name,publisher,count_of_issues,start_year FROM Volumes WHERE id=? AND source_name=?",
+                "SELECT source_name,id,name,publisher,count_of_issues,start_year,aliases FROM Volumes"
+                " WHERE id=? AND source_name=?",
                [volume_id, source_name],
            )

@ -330,6 +339,7 @@ class ComicCacher:
                    "count_of_issues": row[4],
                    "start_year": row[5],
                    "publisher": {"name": row[3]},
+                    "aliases": row[6],
                }
            )

@ -352,7 +362,7 @@ class ComicCacher:

            cur.execute(
                (
-                    "SELECT source_name,id,name,issue_number,site_detail_url,cover_date,super_url,thumb_url,description"
+                    "SELECT source_name,id,name,issue_number,site_detail_url,cover_date,super_url,thumb_url,description,aliases"
                    " FROM Issues WHERE volume_id=? AND source_name=?"
                ),
                [volume_id, source_name],
@ -370,6 +380,7 @@ class ComicCacher:
                        "cover_date": row[5],
                        "image": {"super_url": row[6], "thumb_url": row[7]},
                        "description": row[8],
+                        "aliases": row[9],
                    }
                )

--- a/comictaggerlib/comicvinetalker.py
+++ b/comictaggerlib/comicvinetalker.py
@ -91,11 +91,12 @@ class ComicVineTalker:

        return "Comic Vine rate limit exceeded.  Please wait a bit."

-    def __init__(self) -> None:
+    def __init__(self, series_match_thresh: int = 90) -> None:
        # Identity name for the information source
        self.source_name = "comicvine"

        self.wait_for_rate_limit = False
+        self.series_match_thresh = series_match_thresh

        # key that is registered to comictagger
        default_api_key = "27431e6787042105bd3e47e169a624521f89f3a4"
@ -227,7 +228,7 @@ class ComicVineTalker:
            "format": "json",
            "resources": "volume",
            "query": search_series_name,
-            "field_list": "volume,name,id,start_year,publisher,image,description,count_of_issues",
+            "field_list": "volume,name,id,start_year,publisher,image,description,count_of_issues,aliases",
            "page": 1,
            "limit": 100,
        }
@ -245,10 +246,8 @@ class ComicVineTalker:
        # ORed together, and we get thousands of results.  Good news is the
        # results are sorted by relevance, so we can be smart about halting the search.
        # 1. Don't fetch more than some sane amount of pages.
-        max_results = 500
-        # 2. Halt when not all of our search terms are present in a result
-        # 3. Halt when the results contain more (plus threshold) words than our search
-        result_word_count_max = len(search_series_name.split()) + 3
+        # 2. Halt when any result on the current page is less than or equal to a set ratio using thefuzz
+        max_results = 500  # 5 pages

        total_result_count = min(total_result_count, max_results)

@ -267,19 +266,11 @@ class ComicVineTalker:
        while current_result_count < total_result_count:

            if not literal:
-                # Sanitize the series name for comicvine searching, comicvine search ignore symbols
-                last_result = utils.sanitize_title(search_results[-1]["name"])
-
-                # See if the last result's name has all the of the search terms.
-                # If not, break out of this, loop, we're done.
-                for term in search_series_name.split():
-                    if term not in last_result:
-                        stop_searching = True
-                        break
-
-                # Also, stop searching when the word count of last results is too much longer than our search terms list
-                if len(last_result) > result_word_count_max:
-                    stop_searching = True
+                # Stop searching once any entry falls below the threshold
+                stop_searching = any(
+                    not utils.titles_match(search_series_name, volume["name"], self.series_match_thresh)
+                    for volume in cast(list[CVVolumeResults], cv_response["results"])
+                )

                if stop_searching:
                    break
@ -297,17 +288,6 @@ class ComicVineTalker:
            if callback is not None:
                callback(current_result_count, total_result_count)

-        # Literal searches simply return the matches no extra processing is doneo
-        if not literal:
-            # Remove any search results that don't contain all the search terms (iterate backwards for easy removal)
-            for record in reversed(search_results):
-                # Sanitize the series name for comicvine searching, comicvine search ignore symbols
-                record_name = utils.sanitize_title(record["name"])
-                for term in search_series_name.split():
-                    if term not in record_name:
-                        search_results.remove(record)
-                        break
-
        # Cache these search results, even if it's literal we cache the results
        # The most it will cause is extra processing time
        cvc.add_search_results(self.source_name, series_name, search_results)
@ -328,7 +308,7 @@ class ComicVineTalker:
        params = {
            "api_key": self.api_key,
            "format": "json",
-            "field_list": "name,id,start_year,publisher,count_of_issues",
+            "field_list": "name,id,start_year,publisher,count_of_issues,aliases",
        }
        cv_response = self.get_cv_content(volume_url, params)

@ -351,7 +331,7 @@ class ComicVineTalker:
            "api_key": self.api_key,
            "filter": "volume:" + str(series_id),
            "format": "json",
-            "field_list": "id,volume,issue_number,name,image,cover_date,site_detail_url,description",
+            "field_list": "id,volume,issue_number,name,image,cover_date,site_detail_url,description,aliases",
            "offset": 0,
        }
        cv_response = self.get_cv_content(self.api_base_url + "/issues/", params)
@ -395,7 +375,7 @@ class ComicVineTalker:
        params: dict[str, str | int] = {
            "api_key": self.api_key,
            "format": "json",
-            "field_list": "id,volume,issue_number,name,image,cover_date,site_detail_url,description",
+            "field_list": "id,volume,issue_number,name,image,cover_date,site_detail_url,description,aliases",
            "filter": flt,
        }

--- a/comictaggerlib/issueidentifier.py
+++ b/comictaggerlib/issueidentifier.py
@ -95,7 +95,7 @@ class IssueIdentifier:

        # used to eliminate series names that are too long based on our search
        # string
-        self.length_delta_thresh = settings.id_length_delta_thresh
+        self.series_match_thresh = settings.id_series_match_identify_thresh

        # used to eliminate unlikely publishers
        self.publisher_filter = [s.strip().casefold() for s in settings.id_publisher_filter.split(",")]
@ -120,8 +120,8 @@ class IssueIdentifier:
    def set_additional_metadata(self, md: GenericMetadata) -> None:
        self.additional_metadata = md

-    def set_name_length_delta_threshold(self, delta: int) -> None:
-        self.length_delta_thresh = delta
+    def set_name_series_match_threshold(self, delta: int) -> None:
+        self.series_match_thresh = delta

    def set_publisher_filter(self, flt: list[str]) -> None:
        self.publisher_filter = flt
@ -398,7 +398,7 @@ class IssueIdentifier:
        if keys["month"] is not None:
            self.log_msg("\tMonth:  " + str(keys["month"]))

-        comic_vine = ComicVineTalker()
+        comic_vine = ComicVineTalker(self.settings.id_series_match_search_thresh)
        comic_vine.wait_for_rate_limit = self.wait_and_retry_on_rate_limit

        comic_vine.set_log_func(self.output_function)
@ -433,15 +433,13 @@ class IssueIdentifier:
                if int(keys["year"]) < int(item["start_year"]):
                    date_approved = False

-            # assume that our search name is close to the actual name, say
-            # within ,e.g. 5 chars
-            # sanitize both the search string and the result so that
-            # we are comparing the same type of data
-            shortened_key = utils.sanitize_title(keys["series"])
-            shortened_item_name = utils.sanitize_title(item["name"])
-            if len(shortened_item_name) < (len(shortened_key) + self.length_delta_thresh):
-                length_approved = True
-
+            aliases = []
+            if item["aliases"]:
+                aliases = item["aliases"].split("\n")
+            for name in [item["name"], *aliases]:
+                if utils.titles_match(keys["series"], name, self.series_match_thresh):
+                    length_approved = True
+                    break
            # remove any series from publishers on the filter
            if item["publisher"] is not None:
                publisher = item["publisher"]["name"]
--- a/comictaggerlib/issueselectionwindow.py
+++ b/comictaggerlib/issueselectionwindow.py
@ -97,7 +97,7 @@ class IssueSelectionWindow(QtWidgets.QDialog):
        QtWidgets.QApplication.setOverrideCursor(QtGui.QCursor(QtCore.Qt.CursorShape.WaitCursor))

        try:
-            comic_vine = ComicVineTalker()
+            comic_vine = ComicVineTalker(self.settings.id_series_match_search_thresh)
            comic_vine.fetch_volume_data(self.series_id)
            self.issue_list = comic_vine.fetch_issues_by_volume(self.series_id)
        except ComicVineTalkerException as e:
--- a/comictaggerlib/resulttypes.py
+++ b/comictaggerlib/resulttypes.py
@ -93,6 +93,7 @@ class CVIssuesResults(TypedDict):
    name: str
    site_detail_url: str
    volume: NotRequired[CVVolume]
+    aliases: str


 class CVPublisher(TypedDict, total=False):
@ -110,6 +111,7 @@ class CVVolumeResults(TypedDict):
    publisher: CVPublisher
    start_year: str
    resource_type: NotRequired[str]
+    aliases: NotRequired[str | None]


 class CVCredits(TypedDict):
--- a/comictaggerlib/settings.py
+++ b/comictaggerlib/settings.py
@ -78,7 +78,8 @@ class ComicTaggerSettings:
        self.last_filelist_sorted_order = 0

        # identifier settings
-        self.id_length_delta_thresh = 5
+        self.id_series_match_search_thresh = 90
+        self.id_series_match_identify_thresh = 91
        self.id_publisher_filter = "Panini Comics, Abril, Planeta DeAgostini, Editorial Televisa, Dino Comics"

        # Show/ask dialog flags
@ -217,8 +218,10 @@ class ComicTaggerSettings:
        if self.config.has_option("auto", "last_filelist_sorted_order"):
            self.last_filelist_sorted_order = self.config.getint("auto", "last_filelist_sorted_order")

-        if self.config.has_option("identifier", "id_length_delta_thresh"):
-            self.id_length_delta_thresh = self.config.getint("identifier", "id_length_delta_thresh")
+        if self.config.has_option("identifier", "id_series_match_search_thresh"):
+            self.id_series_match_search_thresh = self.config.getint("identifier", "id_series_match_search_thresh")
+        if self.config.has_option("identifier", "id_series_match_identify_thresh"):
+            self.id_series_match_identify_thresh = self.config.getint("identifier", "id_series_match_identify_thresh")
        if self.config.has_option("identifier", "id_publisher_filter"):
            self.id_publisher_filter = self.config.get("identifier", "id_publisher_filter")

@ -352,7 +355,8 @@ class ComicTaggerSettings:
        if not self.config.has_section("identifier"):
            self.config.add_section("identifier")

-        self.config.set("identifier", "id_length_delta_thresh", self.id_length_delta_thresh)
+        self.config.set("identifier", "id_series_match_search_thresh", self.id_series_match_search_thresh)
+        self.config.set("identifier", "id_series_match_identify_thresh", self.id_series_match_identify_thresh)
        self.config.set("identifier", "id_publisher_filter", self.id_publisher_filter)

        if not self.config.has_section("dialogflags"):
--- a/comictaggerlib/settingswindow.py
+++ b/comictaggerlib/settingswindow.py
@ -155,13 +155,16 @@ class SettingsWindow(QtWidgets.QDialog):
        self.lblDefaultSettings.setText("Revert to default " + self.name.casefold())
        self.btnResetSettings.setText("Default " + self.name)

-        nldt_tip = """<html>The <b>Default Name Length Match Tolerance</b> is for eliminating automatic
-                search matches that are too long compared to your series name search. The higher
+        nmit_tip = """<html>The <b>Name Match Ratio Threshold: Auto-Identify</b> is for eliminating automatic
+                search matches that are too long compared to your series name search. The lower
                it is, the more likely to have a good match, but each search will take longer and
-                use more bandwidth. Too low, and only the very closest lexical matches will be
-                explored.</html>"""
+                use more bandwidth. Too high, and only the very closest matches will be explored.</html>"""
+        nmst_tip = """<html>The <b>Name Match Ratio Threshold: Search</b> is for reducing the total
+                number of results that are returned from a search. The lower it is, the more pages will
+                be returned (max 5 pages or 500 results)</html>"""

-        self.leNameLengthDeltaThresh.setToolTip(nldt_tip)
+        self.sbNameMatchIdentifyThresh.setToolTip(nmit_tip)
+        self.sbNameMatchSearchThresh.setToolTip(nmst_tip)

        pbl_tip = """<html>
            The <b>Publisher Filter</b> is for eliminating automatic matches to certain publishers
@ -173,9 +176,6 @@ class SettingsWindow(QtWidgets.QDialog):
        validator = QtGui.QIntValidator(1, 4, self)
        self.leIssueNumPadding.setValidator(validator)

-        validator = QtGui.QIntValidator(0, 99, self)
-        self.leNameLengthDeltaThresh.setValidator(validator)
-
        self.leRenameTemplate.setToolTip(f"<pre>{html.escape(template_tooltip)}</pre>")
        self.settings_to_form()
        self.rename_error: Exception | None = None
@ -225,7 +225,8 @@ class SettingsWindow(QtWidgets.QDialog):
    def settings_to_form(self) -> None:
        # Copy values from settings to form
        self.leRarExePath.setText(self.settings.rar_exe_path)
-        self.leNameLengthDeltaThresh.setText(str(self.settings.id_length_delta_thresh))
+        self.sbNameMatchIdentifyThresh.setValue(self.settings.id_series_match_identify_thresh)
+        self.sbNameMatchSearchThresh.setValue(self.settings.id_series_match_search_thresh)
        self.tePublisherFilter.setPlainText(self.settings.id_publisher_filter)

        self.cbxCheckForNewVersion.setChecked(self.settings.check_for_new_version)
@ -287,15 +288,13 @@ class SettingsWindow(QtWidgets.QDialog):
        if self.settings.rar_exe_path:
            utils.add_to_path(os.path.dirname(self.settings.rar_exe_path))

-        if not str(self.leNameLengthDeltaThresh.text()).isdigit():
-            self.leNameLengthDeltaThresh.setText("0")
-
        if not str(self.leIssueNumPadding.text()).isdigit():
            self.leIssueNumPadding.setText("0")

        self.settings.check_for_new_version = self.cbxCheckForNewVersion.isChecked()

-        self.settings.id_length_delta_thresh = int(self.leNameLengthDeltaThresh.text())
+        self.settings.id_series_match_identify_thresh = self.sbNameMatchIdentifyThresh.value()
+        self.settings.id_series_match_search_thresh = self.sbNameMatchSearchThresh.value()
        self.settings.id_publisher_filter = str(self.tePublisherFilter.toPlainText())

        self.settings.complicated_parser = self.cbxComplicatedParser.isChecked()
--- a/comictaggerlib/taggerwindow.py
+++ b/comictaggerlib/taggerwindow.py
@ -1064,7 +1064,7 @@ Have fun!
            self.form_to_metadata()

            try:
-                comic_vine = ComicVineTalker()
+                comic_vine = ComicVineTalker(self.settings.id_series_match_search_thresh)
                new_metadata = comic_vine.fetch_issue_data(selector.volume_id, selector.issue_number, self.settings)
            except ComicVineTalkerException as e:
                QtWidgets.QApplication.restoreOverrideCursor()
@ -1674,7 +1674,7 @@ Have fun!
        QtWidgets.QApplication.setOverrideCursor(QtGui.QCursor(QtCore.Qt.CursorShape.WaitCursor))

        try:
-            comic_vine = ComicVineTalker()
+            comic_vine = ComicVineTalker(self.settings.id_series_match_search_thresh)
            comic_vine.wait_for_rate_limit = self.settings.wait_and_retry_on_rate_limit
            cv_md = comic_vine.fetch_issue_data(match["volume_id"], match["issue_number"], self.settings)
        except ComicVineTalkerException:
@ -1743,7 +1743,7 @@ Have fun!
        ii.cover_page_index = md.get_cover_page_index_list()[0]
        if self.atprogdialog is not None:
            ii.set_cover_url_callback(self.atprogdialog.set_test_image)
-        ii.set_name_length_delta_threshold(dlg.name_length_match_tolerance)
+        ii.set_name_series_match_threshold(dlg.name_length_match_tolerance)

        matches: list[IssueResult] = ii.search()

--- a/comictaggerlib/ui/autotagstartwindow.ui
+++ b/comictaggerlib/ui/autotagstartwindow.ui
@ -44,6 +44,16 @@
   </item>
   <item row="1" column="0">
    <layout class="QGridLayout" name="gridLayout">
+     <item row="6" column="0">
+      <widget class="QCheckBox" name="cbxAutoImprint">
+       <property name="toolTip">
+        <string>Checks the publisher against a list of imprints.</string>
+       </property>
+       <property name="text">
+        <string>Auto Imprint</string>
+       </property>
+      </widget>
+     </item>
     <item row="9" column="0">
      <widget class="QCheckBox" name="cbxSpecifySearchString">
       <property name="sizePolicy">
@ -57,19 +67,6 @@
       </property>
      </widget>
     </item>
-     <item row="0" column="0">
-      <widget class="QCheckBox" name="cbxSaveOnLowConfidence">
-       <property name="sizePolicy">
-        <sizepolicy hsizetype="Minimum" vsizetype="Fixed">
-         <horstretch>0</horstretch>
-         <verstretch>0</verstretch>
-        </sizepolicy>
-       </property>
-       <property name="text">
-        <string>Save on low confidence match</string>
-       </property>
-      </widget>
-     </item>
     <item row="4" column="0">
      <widget class="QCheckBox" name="cbxIgnoreLeadingDigitsInFilename">
       <property name="sizePolicy">
@ -83,8 +80,8 @@
       </property>
      </widget>
     </item>
-     <item row="5" column="0">
-      <widget class="QCheckBox" name="cbxRemoveAfterSuccess">
+     <item row="0" column="0">
+      <widget class="QCheckBox" name="cbxSaveOnLowConfidence">
       <property name="sizePolicy">
        <sizepolicy hsizetype="Minimum" vsizetype="Fixed">
         <horstretch>0</horstretch>
@ -92,14 +89,43 @@
        </sizepolicy>
       </property>
       <property name="text">
-        <string>Remove archives from list after successful tagging</string>
+        <string>Save on low confidence match</string>
       </property>
      </widget>
     </item>
-     <item row="3" column="0">
-      <widget class="QCheckBox" name="cbxWaitForRateLimit">
+     <item row="10" column="0">
+      <widget class="QLineEdit" name="leSearchString">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Expanding" vsizetype="Fixed">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+      </widget>
+     </item>
+     <item row="11" column="0">
+      <widget class="QLabel" name="label_3">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Preferred" vsizetype="Fixed">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
       <property name="text">
-        <string>Wait and retry when Comic Vine rate limit is exceeded (experimental)</string>
+        <string>Adjust Name Match Ratio Threshold: Auto-Identify</string>
+       </property>
+      </widget>
+     </item>
+     <item row="8" column="0">
+      <widget class="QCheckBox" name="cbxSplitWords">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Minimum" vsizetype="Fixed">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+       <property name="text">
+        <string>Split words in filenames (e.g. 'judgedredd' to 'judge dredd') (Experimental)</string>
       </property>
      </widget>
     </item>
@ -129,16 +155,6 @@
       </property>
      </widget>
     </item>
-     <item row="6" column="0">
-      <widget class="QCheckBox" name="cbxAutoImprint">
-       <property name="toolTip">
-        <string>Checks the publisher against a list of imprints.</string>
-       </property>
-       <property name="text">
-        <string>Auto Imprint</string>
-       </property>
-      </widget>
-     </item>
     <item row="7" column="0">
      <widget class="QCheckBox" name="cbxRemoveMetadata">
       <property name="toolTip">
@ -149,8 +165,8 @@
       </property>
      </widget>
     </item>
-     <item row="8" column="0">
-      <widget class="QCheckBox" name="cbxSplitWords">
+     <item row="5" column="0">
+      <widget class="QCheckBox" name="cbxRemoveAfterSuccess">
       <property name="sizePolicy">
        <sizepolicy hsizetype="Minimum" vsizetype="Fixed">
         <horstretch>0</horstretch>
@ -158,46 +174,33 @@
        </sizepolicy>
       </property>
       <property name="text">
-        <string>Split words in filenames (e.g. 'judgedredd' to 'judge dredd') (Experimental)</string>
+        <string>Remove archives from list after successful tagging</string>
+       </property>
+      </widget>
+     </item>
+     <item row="3" column="0">
+      <widget class="QCheckBox" name="cbxWaitForRateLimit">
+       <property name="text">
+        <string>Wait and retry when Comic Vine rate limit is exceeded (experimental)</string>
       </property>
      </widget>
     </item>
     <item row="12" column="0">
-      <widget class="QLineEdit" name="leNameLengthMatchTolerance">
-       <property name="sizePolicy">
-        <sizepolicy hsizetype="Expanding" vsizetype="Fixed">
-         <horstretch>0</horstretch>
-         <verstretch>0</verstretch>
-        </sizepolicy>
-       </property>
+      <widget class="QSpinBox" name="sbNameMatchSearchThresh">
       <property name="maximumSize">
        <size>
-         <width>50</width>
+         <width>60</width>
         <height>16777215</height>
        </size>
       </property>
-      </widget>
-     </item>
-     <item row="10" column="0">
-      <widget class="QLineEdit" name="leSearchString">
-       <property name="sizePolicy">
-        <sizepolicy hsizetype="Expanding" vsizetype="Fixed">
-         <horstretch>0</horstretch>
-         <verstretch>0</verstretch>
-        </sizepolicy>
+       <property name="suffix">
+        <string>%</string>
       </property>
-      </widget>
-     </item>
-     <item row="11" column="0">
-      <widget class="QLabel" name="label_3">
-       <property name="sizePolicy">
-        <sizepolicy hsizetype="Preferred" vsizetype="Fixed">
-         <horstretch>0</horstretch>
-         <verstretch>0</verstretch>
-        </sizepolicy>
+       <property name="minimum">
+        <number>1</number>
       </property>
-       <property name="text">
-        <string>Adjust Name Length Match Tolerance:</string>
+       <property name="maximum">
+        <number>100</number>
       </property>
      </widget>
     </item>
--- a/comictaggerlib/ui/settingswindow.ui
+++ b/comictaggerlib/ui/settingswindow.ui
@ -139,7 +139,7 @@
         <item row="0" column="0">
          <widget class="QLabel" name="label_5">
           <property name="text">
-            <string>&lt;html&gt;&lt;head/&gt;&lt;body&gt;&lt;p&gt;These settings are for the automatic issue identifier which searches online for matches. They will not affect &amp;quot;manual&amp;quot; searching.&lt;/p&gt;&lt;p&gt;Hover the mouse over an entry field for more info.&lt;/p&gt;&lt;/body&gt;&lt;/html&gt;</string>
+            <string>&lt;html&gt;&lt;head/&gt;&lt;body&gt;&lt;p&gt;These settings are for the automatic issue identifier which searches online for matches. &lt;/p&gt;&lt;p&gt;Hover the mouse over an entry field for more info.&lt;/p&gt;&lt;/body&gt;&lt;/html&gt;</string>
           </property>
           <property name="wordWrap">
            <bool>true</bool>
@ -164,47 +164,28 @@
              <string/>
             </property>
             <property name="text">
-              <string>Default Name Length Match Tolerance:</string>
+              <string>Default Name Match Ratio Threshold: Search:</string>
             </property>
            </widget>
           </item>
-           <item row="0" column="1">
-            <widget class="QLineEdit" name="leNameLengthDeltaThresh">
-             <property name="sizePolicy">
-              <sizepolicy hsizetype="Maximum" vsizetype="Fixed">
-               <horstretch>0</horstretch>
-               <verstretch>0</verstretch>
-              </sizepolicy>
+           <item row="1" column="0">
+            <widget class="QLabel" name="label">
+             <property name="text">
+              <string>Default Name Match Ratio Threshold: Auto-Identify:</string>
             </property>
-             <property name="maximumSize">
-              <size>
-               <width>50</width>
-               <height>16777215</height>
-              </size>
-             </property>
-             <property name="toolTip">
-              <string/>
+             <property name="alignment">
+              <set>Qt::AlignRight|Qt::AlignTrailing|Qt::AlignVCenter</set>
             </property>
            </widget>
           </item>
           <item row="2" column="0">
-            <widget class="QLabel" name="label_4">
+            <widget class="QLabel" name="label_9">
             <property name="text">
-              <string>Publisher Filter:</string>
+              <string>Always use Publisher Filter on &quot;manual&quot; searches:</string>
             </property>
            </widget>
           </item>
           <item row="2" column="1">
-            <widget class="QPlainTextEdit" name="tePublisherFilter">
-             <property name="sizePolicy">
-              <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
-               <horstretch>0</horstretch>
-               <verstretch>0</verstretch>
-              </sizepolicy>
-             </property>
-            </widget>
-           </item>
-           <item row="1" column="1">
            <widget class="QCheckBox" name="cbxUseFilter">
             <property name="toolTip">
              <string>&lt;html&gt;&lt;head/&gt;&lt;body&gt;&lt;p&gt;Applies the &lt;span style=&quot; font-weight:600;&quot;&gt;Publisher Filter&lt;/span&gt; on all searches.&lt;br/&gt;The search window has a dynamic toggle to show the unfiltered results.&lt;/p&gt;&lt;/body&gt;&lt;/html&gt;</string>
@ -214,10 +195,58 @@
             </property>
            </widget>
           </item>
-           <item row="1" column="0">
-            <widget class="QLabel" name="label_9">
+           <item row="3" column="0">
+            <widget class="QLabel" name="label_4">
             <property name="text">
-              <string>Always use Publisher Filter on &quot;manual&quot; searches:</string>
+              <string>Publisher Filter:</string>
+             </property>
+            </widget>
+           </item>
+           <item row="3" column="1">
+            <widget class="QPlainTextEdit" name="tePublisherFilter">
+             <property name="sizePolicy">
+              <sizepolicy hsizetype="Expanding" vsizetype="Expanding">
+               <horstretch>0</horstretch>
+               <verstretch>0</verstretch>
+              </sizepolicy>
+             </property>
+            </widget>
+           </item>
+           <item row="0" column="1">
+            <widget class="QSpinBox" name="sbNameMatchSearchThresh">
+             <property name="maximumSize">
+              <size>
+               <width>60</width>
+               <height>16777215</height>
+              </size>
+             </property>
+             <property name="suffix">
+              <string>%</string>
+             </property>
+             <property name="minimum">
+              <number>1</number>
+             </property>
+             <property name="maximum">
+              <number>100</number>
+             </property>
+            </widget>
+           </item>
+           <item row="1" column="1">
+            <widget class="QSpinBox" name="sbNameMatchIdentifyThresh">
+             <property name="maximumSize">
+              <size>
+               <width>60</width>
+               <height>16777215</height>
+              </size>
+             </property>
+             <property name="suffix">
+              <string>%</string>
+             </property>
+             <property name="minimum">
+              <number>1</number>
+             </property>
+             <property name="maximum">
+              <number>100</number>
             </property>
            </widget>
           </item>
--- a/comictaggerlib/volumeselectionwindow.py
+++ b/comictaggerlib/volumeselectionwindow.py
@ -42,7 +42,7 @@ class SearchThread(QtCore.QThread):
    searchComplete = pyqtSignal()
    progressUpdate = pyqtSignal(int, int)

-    def __init__(self, series_name: str, refresh: bool, literal: bool = False) -> None:
+    def __init__(self, series_name: str, refresh: bool, literal: bool = False, series_match_thresh: int = 90) -> None:
        QtCore.QThread.__init__(self)
        self.series_name = series_name
        self.refresh: bool = refresh
@ -50,9 +50,10 @@ class SearchThread(QtCore.QThread):
        self.cv_error = False
        self.cv_search_results: list[CVVolumeResults] = []
        self.literal = literal
+        self.series_match_thresh = series_match_thresh

    def run(self) -> None:
-        comic_vine = ComicVineTalker()
+        comic_vine = ComicVineTalker(self.series_match_thresh)
        try:
            self.cv_error = False
            self.cv_search_results = comic_vine.search_for_series(
@ -176,7 +177,6 @@ class VolumeSelectionWindow(QtWidgets.QDialog):
        self.perform_query(refresh=False)

    def auto_select(self) -> None:
-
        if self.comic_archive is None:
            QtWidgets.QMessageBox.information(self, "Auto-Select", "You need to load a comic first!")
            return
@ -310,7 +310,9 @@ class VolumeSelectionWindow(QtWidgets.QDialog):
        self.progdialog.canceled.connect(self.search_canceled)
        self.progdialog.setModal(True)
        self.progdialog.setMinimumDuration(300)
-        self.search_thread = SearchThread(self.series_name, refresh, self.literal)
+        self.search_thread = SearchThread(
+            self.series_name, refresh, self.literal, self.settings.id_series_match_search_thresh
+        )
        self.search_thread.searchComplete.connect(self.search_complete)
        self.search_thread.progressUpdate.connect(self.search_progress_update)
        self.search_thread.start()
--- a/requirements.txt
+++ b/requirements.txt
@ -7,5 +7,6 @@ py7zr
 pycountry
 requests==2.*
 text2digits
+thefuzz[speedup]>=0.19.0
 typing_extensions
 wordninja
--- a/testing/comicdata.py
+++ b/testing/comicdata.py
@ -15,6 +15,7 @@ search_results = [
        name="test",
        publisher=comictaggerlib.resulttypes.CVPublisher(name="test"),
        start_year="",  # This is currently submitted as a string and returned as an int
+        aliases=None,
    ),
    comictaggerlib.resulttypes.CVVolumeResults(
        count_of_issues=1,
@ -24,6 +25,7 @@ search_results = [
        name="test 2",
        publisher=comictaggerlib.resulttypes.CVPublisher(name="test"),
        start_year="",  # This is currently submitted as a string and returned as an int
+        aliases=None,
    ),
 ]

--- a/testing/comicvine.py
+++ b/testing/comicvine.py
@ -98,6 +98,7 @@ cv_volume_result: dict[str, Any] = {
        "count_of_issues": 6,
        "id": 23437,
        "name": "Cory Doctorow's Futuristic Tales of the Here and Now",
+        "aliases": None,
        "publisher": {
            "api_detail_url": "https://comicvine.gamespot.com/api/publisher/4010-1190/",
            "id": 1190,
--- a/tests/comicvinetalker_test.py
+++ b/tests/comicvinetalker_test.py
@ -39,7 +39,7 @@ def test_fetch_issues_by_volume_issue_num_and_year(comicvine_api):
    cv_expected = testing.comicvine.cv_issue_result["results"].copy()
    testing.comicvine.filter_field_list(
        cv_expected,
-        {"params": {"field_list": "id,volume,issue_number,name,image,cover_date,site_detail_url,description"}},
+        {"params": {"field_list": "id,volume,issue_number,name,image,cover_date,site_detail_url,description,aliases"}},
    )
    assert cv[0] == cv_expected