Add configuration instructions to README

README.md

@@ -10,6 +10,33 @@ Put `extract` folder in your pubs `plugs` directory.
 
 Then add `extract` to your plugin list in the pubs configuration file.
 
+## Configuration:
+
+In your pubs configuration file:
+
+```ini
+[plugins]
+active = extract
+
+[[extract]]
+on_import = False
+minimum_similarity = 0.75
+```
+
+If `on_import` is `True` extraction is automatically run whenever a new document is added to the library,
+if false extraction has to be handled manually.
+
+`minimum_similarity` sets the required similarity of an annotation's note and written words to be viewed
+as one. Any annotation that has both and is *under* the minimum similarity will be added in the following form:
+
+```markdown
+> [13] my annotation
+Note: my additional thoughts
+```
+
+That is, the extractor detects additional written words by whoever annotated and adds them to the extraction.
+The option generally should not take too much tuning, but it is there if you need it.
+
 ## Usage:
 
 `pubs extract [-h|-w|-e] <citekeys>`
@@ -62,6 +89,18 @@ What follows is a not-very-sorted train of though on where the plugin is at and
 could see myself taking it one day, provided I find the time.
 Pull requests tackling one of these areas of course very welcome.
 
+## Issues
+
+A note on the extraction. Highlights in pdfs are somewhat difficult to parse
+(as are most things in them). Sometimes they contain the selected text that is written on the
+page, sometimes they contain the annotators thoughts as a note, sometimes they contain nothing.
+This plugin makes an effort to find the right combination and extract the written words,
+as well as any additional notes made - but things *will* slip through or extract weirdly every now
+and again.
+
+The easiest extraction is provided if your program writes the selection itself into the highlight
+content, because then we can just use that. It is harder to parse if it does not.
+
 ## Roadmap:
 
 - [x] extracts highlights and annotations from a doc file (e.g. using PyMuPDF)
@@ -79,6 +118,7 @@ Pull requests tackling one of these areas of course very welcome.
     - [ ] colors are given in very exact 0.6509979 RGB values, meaning we could once again estimate if a color is 'close enough' in distance to tag it accordingly
 - [ ] make invoking the command run a query if corresponding option provided (or whatever) in pubs syntax and use resulting papers
     - [ ] confirm for many papers?
+- [ ] warning when the amount of annotations in file is different than the amount extracted?
 
 ## Things that would also be nice in pubs in general and don't really belong in this repository
 

extract/extract.py

@@ -2,6 +2,7 @@ import os
 import argparse
 
 import fitz
+import Levenshtein
 
 from pubs.plugins import PapersPlugin
 from pubs.events import DocAddEvent, NoteEvent
@@ -39,6 +40,7 @@ class ExtractPlugin(PapersPlugin):
         # or `:: {annotation} :: {page} ::`
         # and so on
         self.onimport = conf["plugins"].get("extract", {}).get("onimport", False)
+        self.minimum_similarity = float(conf["plugins"].get("extract", {}).get("minimum_similarity", 0.75))
 
     def update_parser(self, subparsers, conf):
         """Allow the usage of the pubs extract subcommand"""
@@ -129,13 +131,29 @@ class ExtractPlugin(PapersPlugin):
         with fitz.Document(filename) as doc:
             for page in doc:
                 for annot in page.annots():
-                    content = annot.get_text() or annot.info["content"].replace(
+                    content = self._retrieve_annotation_content(page, annot)
-                        "\n", ""
-                    )
                     if content:
                         annotations.append(f"[{(page.number or 0) + 1}] {content}")
         return annotations
 
+    def _retrieve_annotation_content(self, page, annotation, connector = "\nNote: "):
+        """Gets the text content of an annotation.
+
+        Returns the actual content of an annotation. Sometimes
+        that is only the written words, sometimes that is only
+        annotation notes, sometimes it is both. Runs a similarity
+        comparison between strings to find out whether they
+        should both be included or are doubling up.
+        """
+        content = annotation.info["content"].replace("\n", " ")
+        written = page.get_textbox(annotation.rect).replace("\n", " ")
+
+        if Levenshtein.ratio(content,written) > self.minimum_similarity:
+            return content
+        elif content:
+            return f"{written}{connector}{content}"
+        return written
+
     def _to_stdout(self, annotated_papers):
         """Write annotations to stdout.
 

poetry.lock

@@ -101,6 +101,121 @@ files = [
     {file = "idna-3.4.tar.gz", hash = "sha256:814f528e8dead7d329833b91c5faa87d60bf71824cd12a7530b5526063d02cb4"},
 ]
 
+[[package]]
+name = "levenshtein"
+version = "0.20.8"
+description = "Python extension for computing string edit distances and similarities."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "Levenshtein-0.20.8-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:0e8c505bfb2b64d4d14a6e9f9d115877d150a398a09a97b7827df4711f1e5b4b"},
+    {file = "Levenshtein-0.20.8-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:49bbdd707f435ad0c0e8c2727dd07233ff1db52ac607f9a67f18bf1eb275de66"},
+    {file = "Levenshtein-0.20.8-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:3bf05b99f268330a833f4749b35bf84a31985ae2a52d228207efa3e2863ba832"},
+    {file = "Levenshtein-0.20.8-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b42f81d9fd1c89fe57f17288032b93020eff9ece58a2b8fbea77fc60bc321c11"},
+    {file = "Levenshtein-0.20.8-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f71e89af67e7eb8eed11178711cc23e151e29fe488017cfc56a0a644c5e5d19d"},
+    {file = "Levenshtein-0.20.8-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e614c3d02693f2355c42638753c4de7f5682265691a8bd7fd7d7e1fb6372f7e2"},
+    {file = "Levenshtein-0.20.8-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9039bbcdb306b74542e36aa72fd3afa16db67516bbab65cbfd7ad10480b13c64"},
+    {file = "Levenshtein-0.20.8-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:97a5424784b4c0989b2ec227ae000e80b293d7cc1bd3b02866d7943a3cf6b65c"},
+    {file = "Levenshtein-0.20.8-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:8b6e23ec767c8985a381869d3cb3935f8e67e57b80cbbdb5986329bb75f348b5"},
+    {file = "Levenshtein-0.20.8-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:5201b798e0905adab04c8b9d6ff5dd6cae13456b3e390fcd099991ce4fd32967"},
+    {file = "Levenshtein-0.20.8-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:744d374f8227624028642d078ae4692f73e9e53b0ff87d25232e75abe842b00c"},
+    {file = "Levenshtein-0.20.8-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:d6b247b22703d1989cb97a0b26485db7a3397322d3975c974c22e10a1592a414"},
+    {file = "Levenshtein-0.20.8-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:ff3e7e6a58892ee30f90507a4da1d316e0c3e8e3f1f70b694eeedc397a3d0802"},
+    {file = "Levenshtein-0.20.8-cp310-cp310-win32.whl", hash = "sha256:ef65c16113028688353b10d159b6f12a6a471890ea6aa466a0626cd11c9239a5"},
+    {file = "Levenshtein-0.20.8-cp310-cp310-win_amd64.whl", hash = "sha256:a8aac56e669a733e03c81b2e015dcd8d287db716bf2c6c9a480c4227300a7c52"},
+    {file = "Levenshtein-0.20.8-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:96070d1a1c0d908d65cd9765a7b63ecafa8ef52d7a6460dccdf4d1bd29ad98fd"},
+    {file = "Levenshtein-0.20.8-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:079a216a55a3735f59661e0b25ff3a2122e18a710682d88e0d7576bff594f547"},
+    {file = "Levenshtein-0.20.8-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d5cba3eab536188f16115ab6ea5de1e19440c35bb01c817388e3696b811bca21"},
+    {file = "Levenshtein-0.20.8-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e0963497f51ff5aa73447173178daefff4a80e4165c2575d1357503c030f0a6b"},
+    {file = "Levenshtein-0.20.8-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d140a0a450813ef8658f2a87d5c7d9ea2fff3f8b8d80e7ac80061b21c6a733f0"},
+    {file = "Levenshtein-0.20.8-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:dd2c3a10c7d5d1ddb181121d7a038918408efb92206519428bcee6fe6a9fec30"},
+    {file = "Levenshtein-0.20.8-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:59a9067d5a9b63ec5ce7e23624dfe2c26438deecb3e46103fa68c72baef544ec"},
+    {file = "Levenshtein-0.20.8-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6c587c15278877e6974f2899c2bc15e561f762a71c2b8d8771de88c650738d87"},
+    {file = "Levenshtein-0.20.8-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:a66a3ef2e58ac7eb8f96ae8ba8b9aec34d1446865faaeab86d3559b9a0d422aa"},
+    {file = "Levenshtein-0.20.8-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:6b3745a6c1dee2178feab4e37ee46669ea2a7b8122eb63803e96547fff9bf1fc"},
+    {file = "Levenshtein-0.20.8-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:404d30d0d4b36ea504b30c508107327fa06b2cdae88291d1864b236744858ac5"},
+    {file = "Levenshtein-0.20.8-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:7dc85e9d8a74af873621d2b26e04aa1f41e02588a98dc859bc448e5c04aebb2a"},
+    {file = "Levenshtein-0.20.8-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:b134a8f6fa42355baf6687c7c6890f82672de95ea44fdb59f99696087ec19439"},
+    {file = "Levenshtein-0.20.8-cp311-cp311-win32.whl", hash = "sha256:e48dd2f143f2236717a7604fed2dc2e078b96a0c3881e490f258a5f4bde11324"},
+    {file = "Levenshtein-0.20.8-cp311-cp311-win_amd64.whl", hash = "sha256:43505eb89a80ea529c019391809c6fbf552eb5b4a5e34780c842b0f324d2b769"},
+    {file = "Levenshtein-0.20.8-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:d3e14702351d7c844aaef5fe1ffc53f590e4e6a17b12836517f9771379b0da49"},
+    {file = "Levenshtein-0.20.8-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:71f0c835dc7a8fd7a8b94374bb60ad238fbf7a4264f40868ec4d884130b8d96f"},
+    {file = "Levenshtein-0.20.8-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:6cf9c8a45ce9fd60ff0fcdd5cfa44c83f2d2a0188c9e85d7eef36579919cb574"},
+    {file = "Levenshtein-0.20.8-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:940c193991eb12922f76c422946f6c3d30ad144233c0b49dfa48e132a445cbcb"},
+    {file = "Levenshtein-0.20.8-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3f8d2d36c1d8ad9a699b1b41948c08161d4c645921ddb643b1d478b8457c859a"},
+    {file = "Levenshtein-0.20.8-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:477265c6ba07bb01f96e64fe427ec51f63872dcb345f6340f5e5c7403e367282"},
+    {file = "Levenshtein-0.20.8-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:7a9622d9bba7173df575cbfc4bc0a0d929d1733e1eeac85829e4f1ad21a24de5"},
+    {file = "Levenshtein-0.20.8-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:db71d6ea4f2412b06bec7ed697dd2efe4f42ff953db58354364902d8f29587a4"},
+    {file = "Levenshtein-0.20.8-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:828ceb9a947be03dded59d7d44fa8629ab7fc32185e460ada6355d23412ced7c"},
+    {file = "Levenshtein-0.20.8-cp36-cp36m-musllinux_1_1_s390x.whl", hash = "sha256:ede6b8eaeb73aff5714459cbf5c18345fc40ca90b1885bd7e5cf0c27d99f118a"},
+    {file = "Levenshtein-0.20.8-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:1481916946b50c7c80d4d318e290392614a07f9fcc612aadf3c6ce2c685ccbe9"},
+    {file = "Levenshtein-0.20.8-cp36-cp36m-win32.whl", hash = "sha256:f7e4be20d10ffd24723363d4796ea78371c73d961725d7663381bbfa07ad086a"},
+    {file = "Levenshtein-0.20.8-cp36-cp36m-win_amd64.whl", hash = "sha256:e8ecf0a10823ca4c90c42adb79478a845ea4979a751f32bc7cdb3b32e39e9c7f"},
+    {file = "Levenshtein-0.20.8-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:c09cb048098396a3ece6afe032cfdca0bb0fa49d5fb6b146d762e2d45274abba"},
+    {file = "Levenshtein-0.20.8-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:204e8454d9f0be127ae21f0ff05506ed6785937c78d4ed8597504283675fdd79"},
+    {file = "Levenshtein-0.20.8-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2ed457334940a0dff6617e86f7df6b3ff64aa9f5a0571c7bd889228f6a9863f6"},
+    {file = "Levenshtein-0.20.8-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:438d95ca36c8d277fb0cb078eab227173e1a59c6742cdb6dd97f106106e38ffd"},
+    {file = "Levenshtein-0.20.8-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:76ee654d6a741e43039094c9c68396f952d48c4b74d4da1450c87b77db5a7f83"},
+    {file = "Levenshtein-0.20.8-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d0f56896b12f4276a77e774be560d00bd6b173af1a5554554ed86a288ff111a4"},
+    {file = "Levenshtein-0.20.8-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:ba530885bc063ad90e8dff6d7e4cb55e523213ca1815a41ccc67a2efb405ad3b"},
+    {file = "Levenshtein-0.20.8-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:caf6ad0c8c0780d78c3f5eb270fb8aa5820cf423057d252a1de6a79b1f07e76b"},
+    {file = "Levenshtein-0.20.8-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:dae722ee22c610243d6fade46ce04ab16a36862b3edc732a60ccc57a4e9c6af8"},
+    {file = "Levenshtein-0.20.8-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:5d8cb2b06d8e7683c321e20740385545447cb2faf2286e2817ca03745354bf0c"},
+    {file = "Levenshtein-0.20.8-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:130404e7a917c3ba80879cd8fcdd6f6e84e2cdc3018cd225d95fea906be8d8fa"},
+    {file = "Levenshtein-0.20.8-cp37-cp37m-win32.whl", hash = "sha256:73f9db6a178a926c15dd1a8c9ccd810407c3eaddbfc2145f68242b55e238fd85"},
+    {file = "Levenshtein-0.20.8-cp37-cp37m-win_amd64.whl", hash = "sha256:2c38b1005e6b7fe62dfc50c56bd0b7fc85688a7197f6a116459a3107461472e2"},
+    {file = "Levenshtein-0.20.8-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:7b42a6470ee44e80332acc95ed55890d12b5f27676a942e0c268b0092569f06c"},
+    {file = "Levenshtein-0.20.8-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:2f586f3b192805ee19fb56bed803d05966ef0edc544822e934bb106f688d427b"},
+    {file = "Levenshtein-0.20.8-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:4619c165f1fe1048fc22065290b779ac3903d0d75b0fb2c600abc3913993036c"},
+    {file = "Levenshtein-0.20.8-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3512354f28a13e680c5d7e83e9edc23afa5b807895db7933efb0be3fee3d50e1"},
+    {file = "Levenshtein-0.20.8-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:cab33decf636cebb20bf90563e89eb500ccfb758b0af19630ce149606f0b130f"},
+    {file = "Levenshtein-0.20.8-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:675a91e9020a24c53301de11cd4b9b9b07827f93e2ddb56187c7ba2eede58dbc"},
+    {file = "Levenshtein-0.20.8-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c8995f69db76b6c9fc113dc65b9b17a1f04f718f2c18203f6c0ac84a07462c7"},
+    {file = "Levenshtein-0.20.8-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b6463f3bc2a426703b2b259c1d6aaa73bd0c3fc85492c0f4d5dfd60658271ee9"},
+    {file = "Levenshtein-0.20.8-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:085e7a8f5d8a2d71790f2c16363dbd15bdc6b2d66bb12adfeef453d9436fc641"},
+    {file = "Levenshtein-0.20.8-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:94c773c9fb3a90cb7e191087beb06fb49b8d0452fb0f1abf27e9c644b19a0557"},
+    {file = "Levenshtein-0.20.8-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:07836b04b628f9db65f24c34bb63fb453723aadf00b45e093384108ec05ba545"},
+    {file = "Levenshtein-0.20.8-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:feaf0ae11827a917cdb314f189c711e0fb2b677f4e69e2c61276a65f2209ac4e"},
+    {file = "Levenshtein-0.20.8-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:c7b39b572cd3d2c2b8c5753246a52eda3cf3360f49de95e3f671062acc6caaf4"},
+    {file = "Levenshtein-0.20.8-cp38-cp38-win32.whl", hash = "sha256:939b819874903a689863f3a552a90e1742ac342cda80f5d3e8adb42e1729d37e"},
+    {file = "Levenshtein-0.20.8-cp38-cp38-win_amd64.whl", hash = "sha256:d9ad1515424b708608596a1bf314781d240f5b4fd934528d2bf0c9d7d0620e78"},
+    {file = "Levenshtein-0.20.8-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:df4ba85d1c2361b2591d8b8c01740ed9803a7c32d706f1015446f5f382c4b8ec"},
+    {file = "Levenshtein-0.20.8-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:7677c9abbeff907bbd7869e33e47874e6ecf6e4341298e968c9e3dbf4c344765"},
+    {file = "Levenshtein-0.20.8-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:36a479f799613479871da1ed221b7099cb77caf5b060fa9eb916d5b90c0ae206"},
+    {file = "Levenshtein-0.20.8-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:72ac6ae6581a586ef7f325413d4f87c39dc5e50734c5731586c73c7f837af8fc"},
+    {file = "Levenshtein-0.20.8-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7d8cb8a401633ff6210c2fe4cd5a1410b26cef47f42e0e1ab3563c5f94975c4c"},
+    {file = "Levenshtein-0.20.8-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:6456643a8c5de3ced585d9fd4fba8ae78a3b7860bed7a670f76e7a7865b34c78"},
+    {file = "Levenshtein-0.20.8-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:65dc11345ac7d4c13f2392ec3610c392498500a7ba6455408abdd129becea41f"},
+    {file = "Levenshtein-0.20.8-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:55baa3498b31ceb62b54e5278e6f5830b4748b4709fa291e91b7d022f9bef63a"},
+    {file = "Levenshtein-0.20.8-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:9ea2f847e209a463387b8e8d6743b1cd929e60fdce85d8ab19022ba6678546c5"},
+    {file = "Levenshtein-0.20.8-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:2e3eb8e529cad2419d3f4bbb9f5fa0ea845c142b5e17a59c3f4ffe82b1ebfa29"},
+    {file = "Levenshtein-0.20.8-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:4d61ed0b452fb6456be49ab1b9b2f1d6366db611a8c71a2fecab37118010e6c5"},
+    {file = "Levenshtein-0.20.8-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:5bc69cbb75c502492666fd45b345e3f31a8a709b4019146cfc19f331fe1f6b38"},
+    {file = "Levenshtein-0.20.8-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:6b7d71485f4bf92d5cddfdb91a82a0308a7a6b6a216887de44ecdab0c0495ca1"},
+    {file = "Levenshtein-0.20.8-cp39-cp39-win32.whl", hash = "sha256:59da44a59861f60b049178a56c9d723d7181c5e2e6adf04bf54120c2d1d589a1"},
+    {file = "Levenshtein-0.20.8-cp39-cp39-win_amd64.whl", hash = "sha256:8dc2232dd6918aa3f6be80c9c620ce0a0e361b1b979a49d1e3fa831af224e721"},
+    {file = "Levenshtein-0.20.8-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:153ff8e7491f80b72250cabce926922d3d4a623d0846602a3f4fef974c3e7f4d"},
+    {file = "Levenshtein-0.20.8-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e21df20e8d8df9be6b33ed013852ba6a317d139d11647f8b241c894c8b76d523"},
+    {file = "Levenshtein-0.20.8-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7fae73b02e929da1b52d988e54f029347fe9e5b024282c9492cfc4d8a951cd93"},
+    {file = "Levenshtein-0.20.8-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:918a97459df93a8984355f91886f29dc97ddef85dfff185b38b1b748512411a1"},
+    {file = "Levenshtein-0.20.8-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:c4c1e802c746679c765c780fb0dce82af1cc000bc0bea9c37bd4d6d295ddd339"},
+    {file = "Levenshtein-0.20.8-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:d17615b69f01a7db2bd4269e14fdad71bc7c3f08ca7a366914f85b08341953a0"},
+    {file = "Levenshtein-0.20.8-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3a57710c9c35cf41df77f4eb24ae5e9568a2d9fba3010ace657a8ec7d044c871"},
+    {file = "Levenshtein-0.20.8-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:24ffa06dd1a348b45584a192a86ff5ae8233d1c1cea4bd49fa9243485b8cf838"},
+    {file = "Levenshtein-0.20.8-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b714581e760c79ff990d8196bd0978d9246427a93eefb1f9f1087b88e17c594d"},
+    {file = "Levenshtein-0.20.8-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:9e8c5d97068fb4a78f5bfe0f5d8fa365867f2431f399f5df9dd2b741558c3684"},
+    {file = "Levenshtein-0.20.8-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:9d1c2766a63f1231119d6744502913e432c33aa0ceb6fabc536a4fbffcc90a46"},
+    {file = "Levenshtein-0.20.8-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f87c9ed45e05fb9ad800560e3c063b1945cda981b6f92b1abfefb603b8f9113a"},
+    {file = "Levenshtein-0.20.8-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0385d69ccca8bc1a091e1071357b8610af758af8968ed32bedcedf96c51a6bb9"},
+    {file = "Levenshtein-0.20.8-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:98e741e54b7e66a63d92af04193b9d819b8f29292ccfcfd2cc6eee67ab2469f1"},
+    {file = "Levenshtein-0.20.8-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:8746be2afafdab5ffc05094b0a954cea4f95bcc3e2bd48dce04b5e51063aeefb"},
+    {file = "Levenshtein-0.20.8.tar.gz", hash = "sha256:a8cc52849264d3aa6e16c9daca95a02d59e9496c86f18def7131413cfba617cc"},
+]
+
+[package.dependencies]
+rapidfuzz = ">=2.3.0,<3.0.0"
+
 [[package]]
 name = "pubs"
 version = "0.9.0"
@@ -245,6 +360,108 @@ files = [
     {file = "PyYAML-6.0.tar.gz", hash = "sha256:68fb519c14306fec9720a2a5b45bc9f0c8d1b9c72adf45c37baedfcd949c35a2"},
 ]
 
+[[package]]
+name = "rapidfuzz"
+version = "2.13.7"
+description = "rapid fuzzy string matching"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "rapidfuzz-2.13.7-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:b75dd0928ce8e216f88660ab3d5c5ffe990f4dd682fd1709dba29d5dafdde6de"},
+    {file = "rapidfuzz-2.13.7-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:24d3fea10680d085fd0a4d76e581bfb2b1074e66e78fd5964d4559e1fcd2a2d4"},
+    {file = "rapidfuzz-2.13.7-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8109e0324d21993d5b2d111742bf5958f3516bf8c59f297c5d1cc25a2342eb66"},
+    {file = "rapidfuzz-2.13.7-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b5f705652360d520c2de52bee11100c92f59b3e3daca308ebb150cbc58aecdad"},
+    {file = "rapidfuzz-2.13.7-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7496e8779905b02abc0ab4ba2a848e802ab99a6e20756ffc967a0de4900bd3da"},
+    {file = "rapidfuzz-2.13.7-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:24eb6b843492bdc63c79ee4b2f104059b7a2201fef17f25177f585d3be03405a"},
+    {file = "rapidfuzz-2.13.7-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:467c1505362823a5af12b10234cb1c4771ccf124c00e3fc9a43696512bd52293"},
+    {file = "rapidfuzz-2.13.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:53dcae85956853b787c27c1cb06f18bb450e22cf57a4ad3444cf03b8ff31724a"},
+    {file = "rapidfuzz-2.13.7-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:46b9b8aa09998bc48dd800854e8d9b74bc534d7922c1d6e1bbf783e7fa6ac29c"},
+    {file = "rapidfuzz-2.13.7-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:1fbad8fb28d98980f5bff33c7842efef0315d42f0cd59082108482a7e6b61410"},
+    {file = "rapidfuzz-2.13.7-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:43fb8cb030f888c3f076d40d428ed5eb4331f5dd6cf1796cfa39c67bf0f0fc1e"},
+    {file = "rapidfuzz-2.13.7-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:b6bad92de071cbffa2acd4239c1779f66851b60ffbbda0e4f4e8a2e9b17e7eef"},
+    {file = "rapidfuzz-2.13.7-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:d00df2e4a81ffa56a6b1ec4d2bc29afdcb7f565e0b8cd3092fece2290c4c7a79"},
+    {file = "rapidfuzz-2.13.7-cp310-cp310-win32.whl", hash = "sha256:2c836f0f2d33d4614c3fbaf9a1eb5407c0fe23f8876f47fd15b90f78daa64c34"},
+    {file = "rapidfuzz-2.13.7-cp310-cp310-win_amd64.whl", hash = "sha256:c36fd260084bb636b9400bb92016c6bd81fd80e59ed47f2466f85eda1fc9f782"},
+    {file = "rapidfuzz-2.13.7-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:b34e8c0e492949ecdd5da46a1cfc856a342e2f0389b379b1a45a3cdcd3176a6e"},
+    {file = "rapidfuzz-2.13.7-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:875d51b3497439a72e2d76183e1cb5468f3f979ab2ddfc1d1f7dde3b1ecfb42f"},
+    {file = "rapidfuzz-2.13.7-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ae33a72336059213996fe4baca4e0e4860913905c2efb7c991eab33b95a98a0a"},
+    {file = "rapidfuzz-2.13.7-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a5585189b3d90d81ccd62d4f18530d5ac8972021f0aaaa1ffc6af387ff1dce75"},
+    {file = "rapidfuzz-2.13.7-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:42085d4b154a8232767de8296ac39c8af5bccee6b823b0507de35f51c9cbc2d7"},
+    {file = "rapidfuzz-2.13.7-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:585206112c294e335d84de5d5f179c0f932837752d7420e3de21db7fdc476278"},
+    {file = "rapidfuzz-2.13.7-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f891b98f8bc6c9d521785816085e9657212621e93f223917fb8e32f318b2957e"},
+    {file = "rapidfuzz-2.13.7-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:08590905a95ccfa43f4df353dcc5d28c15d70664299c64abcad8721d89adce4f"},
+    {file = "rapidfuzz-2.13.7-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:b5dd713a1734574c2850c566ac4286594bacbc2d60b9170b795bee4b68656625"},
+    {file = "rapidfuzz-2.13.7-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:988f8f6abfba7ee79449f8b50687c174733b079521c3cc121d65ad2d38831846"},
+    {file = "rapidfuzz-2.13.7-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:b3210869161a864f3831635bb13d24f4708c0aa7208ef5baac1ac4d46e9b4208"},
+    {file = "rapidfuzz-2.13.7-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:f6fe570e20e293eb50491ae14ddeef71a6a7e5f59d7e791393ffa99b13f1f8c2"},
+    {file = "rapidfuzz-2.13.7-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:6120f2995f5154057454c5de99d86b4ef3b38397899b5da1265467e8980b2f60"},
+    {file = "rapidfuzz-2.13.7-cp311-cp311-win32.whl", hash = "sha256:b20141fa6cee041917801de0bab503447196d372d4c7ee9a03721b0a8edf5337"},
+    {file = "rapidfuzz-2.13.7-cp311-cp311-win_amd64.whl", hash = "sha256:ec55a81ac2b0f41b8d6fb29aad16e55417036c7563bad5568686931aa4ff08f7"},
+    {file = "rapidfuzz-2.13.7-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:7d005e058d86f2a968a8d28ca6f2052fab1f124a39035aa0523261d6baf21e1f"},
+    {file = "rapidfuzz-2.13.7-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fe59a0c21a032024edb0c8e43f5dee5623fef0b65a1e3c1281836d9ce199af3b"},
+    {file = "rapidfuzz-2.13.7-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cdfc04f7647c29fb48da7a04082c34cdb16f878d3c6d098d62d5715c0ad3000c"},
+    {file = "rapidfuzz-2.13.7-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:68a89bb06d5a331511961f4d3fa7606f8e21237467ba9997cae6f67a1c2c2b9e"},
+    {file = "rapidfuzz-2.13.7-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:effe182767d102cb65dfbbf74192237dbd22d4191928d59415aa7d7c861d8c88"},
+    {file = "rapidfuzz-2.13.7-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:25b4cedf2aa19fb7212894ce5f5219010cce611b60350e9a0a4d492122e7b351"},
+    {file = "rapidfuzz-2.13.7-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:3a9bd02e1679c0fd2ecf69b72d0652dbe2a9844eaf04a36ddf4adfbd70010e95"},
+    {file = "rapidfuzz-2.13.7-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:5e2b3d020219baa75f82a4e24b7c8adcb598c62f0e54e763c39361a9e5bad510"},
+    {file = "rapidfuzz-2.13.7-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:cf62dacb3f9234f3fddd74e178e6d25c68f2067fde765f1d95f87b1381248f58"},
+    {file = "rapidfuzz-2.13.7-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:fa263135b892686e11d5b84f6a1892523123a00b7e5882eff4fbdabb38667347"},
+    {file = "rapidfuzz-2.13.7-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:fa4c598ed77f74ec973247ca776341200b0f93ec3883e34c222907ce72cb92a4"},
+    {file = "rapidfuzz-2.13.7-cp37-cp37m-win32.whl", hash = "sha256:c2523f8180ebd9796c18d809e9a19075a1060b1a170fde3799e83db940c1b6d5"},
+    {file = "rapidfuzz-2.13.7-cp37-cp37m-win_amd64.whl", hash = "sha256:5ada0a14c67452358c1ee52ad14b80517a87b944897aaec3e875279371a9cb96"},
+    {file = "rapidfuzz-2.13.7-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:ca8a23097c1f50e0fdb4de9e427537ca122a18df2eead06ed39c3a0bef6d9d3a"},
+    {file = "rapidfuzz-2.13.7-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:9be02162af0376d64b840f2fc8ee3366794fc149f1e06d095a6a1d42447d97c5"},
+    {file = "rapidfuzz-2.13.7-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:af4f7c3c904ca709493eb66ca9080b44190c38e9ecb3b48b96d38825d5672559"},
+    {file = "rapidfuzz-2.13.7-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1f50d1227e6e2a0e3ae1fb1c9a2e1c59577d3051af72c7cab2bcc430cb5e18da"},
+    {file = "rapidfuzz-2.13.7-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c71d9d512b76f05fa00282227c2ae884abb60e09f08b5ca3132b7e7431ac7f0d"},
+    {file = "rapidfuzz-2.13.7-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b52ac2626945cd21a2487aeefed794c14ee31514c8ae69b7599170418211e6f6"},
+    {file = "rapidfuzz-2.13.7-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ca00fafd2756bc9649bf80f1cf72c647dce38635f0695d7ce804bc0f759aa756"},
+    {file = "rapidfuzz-2.13.7-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d248a109699ce9992304e79c1f8735c82cc4c1386cd8e27027329c0549f248a2"},
+    {file = "rapidfuzz-2.13.7-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:c88adbcb933f6b8612f6c593384bf824e562bb35fc8a0f55fac690ab5b3486e5"},
+    {file = "rapidfuzz-2.13.7-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:c8601a66fbfc0052bb7860d2eacd303fcde3c14e87fdde409eceff516d659e77"},
+    {file = "rapidfuzz-2.13.7-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:27be9c63215d302ede7d654142a2e21f0d34ea6acba512a4ae4cfd52bbaa5b59"},
+    {file = "rapidfuzz-2.13.7-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:3dcffe1f3cbda0dc32133a2ae2255526561ca594f15f9644384549037b355245"},
+    {file = "rapidfuzz-2.13.7-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:8450d15f7765482e86ef9be2ad1a05683cd826f59ad236ef7b9fb606464a56aa"},
+    {file = "rapidfuzz-2.13.7-cp38-cp38-win32.whl", hash = "sha256:460853983ab88f873173e27cc601c5276d469388e6ad6e08c4fd57b2a86f1064"},
+    {file = "rapidfuzz-2.13.7-cp38-cp38-win_amd64.whl", hash = "sha256:424f82c35dbe4f83bdc3b490d7d696a1dc6423b3d911460f5493b7ffae999fd2"},
+    {file = "rapidfuzz-2.13.7-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:c3fbe449d869ea4d0909fc9d862007fb39a584fb0b73349a6aab336f0d90eaed"},
+    {file = "rapidfuzz-2.13.7-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:16080c05a63d6042643ae9b6cfec1aefd3e61cef53d0abe0df3069b9d4b72077"},
+    {file = "rapidfuzz-2.13.7-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:dbcf5371ea704759fcce772c66a07647751d1f5dbdec7818331c9b31ae996c77"},
+    {file = "rapidfuzz-2.13.7-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:114810491efb25464016fd554fdf1e20d390309cecef62587494fc474d4b926f"},
+    {file = "rapidfuzz-2.13.7-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:99a84ab9ac9a823e7e93b4414f86344052a5f3e23b23aa365cda01393ad895bd"},
+    {file = "rapidfuzz-2.13.7-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:81642a24798851b118f82884205fc1bd9ff70b655c04018c467824b6ecc1fabc"},
+    {file = "rapidfuzz-2.13.7-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c3741cb0bf9794783028e8b0cf23dab917fa5e37a6093b94c4c2f805f8e36b9f"},
+    {file = "rapidfuzz-2.13.7-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:759a3361711586a29bc753d3d1bdb862983bd9b9f37fbd7f6216c24f7c972554"},
+    {file = "rapidfuzz-2.13.7-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:1333fb3d603d6b1040e365dca4892ba72c7e896df77a54eae27dc07db90906e3"},
+    {file = "rapidfuzz-2.13.7-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:916bc2e6cf492c77ad6deb7bcd088f0ce9c607aaeabc543edeb703e1fbc43e31"},
+    {file = "rapidfuzz-2.13.7-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:23524635840500ce6f4d25005c9529a97621689c85d2f727c52eed1782839a6a"},
+    {file = "rapidfuzz-2.13.7-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:ebe303cd9839af69dd1f7942acaa80b1ba90bacef2e7ded9347fbed4f1654672"},
+    {file = "rapidfuzz-2.13.7-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:fe56659ccadbee97908132135de4b875543353351e0c92e736b7c57aee298b5a"},
+    {file = "rapidfuzz-2.13.7-cp39-cp39-win32.whl", hash = "sha256:3f11a7eff7bc6301cd6a5d43f309e22a815af07e1f08eeb2182892fca04c86cb"},
+    {file = "rapidfuzz-2.13.7-cp39-cp39-win_amd64.whl", hash = "sha256:e8914dad106dacb0775718e54bf15e528055c4e92fb2677842996f2d52da5069"},
+    {file = "rapidfuzz-2.13.7-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:7f7930adf84301797c3f09c94b9c5a9ed90a9e8b8ed19b41d2384937e0f9f5bd"},
+    {file = "rapidfuzz-2.13.7-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c31022d9970177f6affc6d5dd757ed22e44a10890212032fabab903fdee3bfe7"},
+    {file = "rapidfuzz-2.13.7-pp37-pypy37_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f42b82f268689f429def9ecfb86fa65ceea0eaf3fed408b570fe113311bf5ce7"},
+    {file = "rapidfuzz-2.13.7-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8b477b43ced896301665183a5e0faec0f5aea2373005648da8bdcb3c4b73f280"},
+    {file = "rapidfuzz-2.13.7-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:d63def9bbc6b35aef4d76dc740301a4185867e8870cbb8719ec9de672212fca8"},
+    {file = "rapidfuzz-2.13.7-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:c66546e30addb04a16cd864f10f5821272a1bfe6462ee5605613b4f1cb6f7b48"},
+    {file = "rapidfuzz-2.13.7-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f799d1d6c33d81e983d3682571cc7d993ae7ff772c19b3aabb767039c33f6d1e"},
+    {file = "rapidfuzz-2.13.7-pp38-pypy38_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d82f20c0060ffdaadaf642b88ab0aa52365b56dffae812e188e5bdb998043588"},
+    {file = "rapidfuzz-2.13.7-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:042644133244bfa7b20de635d500eb9f46af7097f3d90b1724f94866f17cb55e"},
+    {file = "rapidfuzz-2.13.7-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:75c45dcd595f8178412367e302fd022860ea025dc4a78b197b35428081ed33d5"},
+    {file = "rapidfuzz-2.13.7-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:3d8b081988d0a49c486e4e845a547565fee7c6e7ad8be57ff29c3d7c14c6894c"},
+    {file = "rapidfuzz-2.13.7-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:16ffad751f43ab61001187b3fb4a9447ec2d1aedeff7c5bac86d3b95f9980cc3"},
+    {file = "rapidfuzz-2.13.7-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:020858dd89b60ce38811cd6e37875c4c3c8d7fcd8bc20a0ad2ed1f464b34dc4e"},
+    {file = "rapidfuzz-2.13.7-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cda1e2f66bb4ba7261a0f4c2d052d5d909798fca557cbff68f8a79a87d66a18f"},
+    {file = "rapidfuzz-2.13.7-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:b6389c50d8d214c9cd11a77f6d501529cb23279a9c9cafe519a3a4b503b5f72a"},
+    {file = "rapidfuzz-2.13.7.tar.gz", hash = "sha256:8d3e252d4127c79b4d7c2ae47271636cbaca905c8bb46d80c7930ab906cf4b5c"},
+]
+
+[package.extras]
+full = ["numpy"]
+
 [[package]]
 name = "requests"
 version = "2.28.1"
@@ -322,4 +539,4 @@ socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "fef247962b563c632703d99f7f7315f66e49cc1625ef026d120ccc84339c05db"
+content-hash = "becf02a3ad8360833ab2a43a36fe0dc224cd028d5713e7de3daf61b6b99959fe"

pyproject.toml

@@ -10,6 +10,7 @@ packages = [{include = "extract"}]
 [tool.poetry.dependencies]
 python = "^3.10"
 pymupdf = "^1.21.1"
+levenshtein = "^0.20.8"
 
 [tool.poetry.group.dev.dependencies]
 pubs = "^0.9.0"