fix(citoid): remove non-numeric chars from oclc

5j9 · Dec 12, 2024 · 17e9e43 · 17e9e43
1 parent 3edd2f5
commit 17e9e43
Show file tree

Hide file tree

Showing 6 changed files with 74 additions and 0 deletions.
diff --git a/lib/citoid.py b/lib/citoid.py
@@ -1,5 +1,8 @@
+from functools import partial
 from urllib.parse import quote_plus
 
+from regex import compile as rc
+
 from lib import four_digit_num, request
 from lib.commons import find_any_date
 
@@ -19,6 +22,8 @@
     'PMCID': 'pmcid',
 }
 
+rm_non_numeric = partial(rc(r'\D').sub, '')
+
 
 def citoid_data(query: str, quote=False, /) -> dict:
     if quote is True:
@@ -38,6 +43,9 @@ def citoid_data(query: str, quote=False, /) -> dict:
         if (value := get(citoid_key)) is not None:
             d[citer_key] = value
 
+    if (oclc := d.get('oclc')) is not None:
+        d['oclc'] = rm_non_numeric(oclc)
+
     authors = get('author')
     contributors = get('contributor')
 

diff --git a/tests/isbn_oclc_test.py b/tests/isbn_oclc_test.py
@@ -137,3 +137,9 @@ def test_not_found_isbn(_m1, _m2):
     with raises(ReturnError) as e:
         isbn_scr('9798863646336')
     assert e.value.args == ('Error: ISBN not found', '', '')
+
+
+def test_oclc_no_leading_letters():
+    assert isbn_scr('978-80-210-8779-8')[1] == (
+        '* {{cite book | title=The European fortune of the Roman Veronica in the Middle Ages | publisher=Brepols | publication-place=Turnhout | date=2017 | isbn=978-80-210-8779-8 | oclc=1021182894 | ref={{sfnref|Brepols|2017}}}}'
+    )
diff --git a/tests/testdata/7b8675b5b8a89b52eaa2a91e1e8c08b10242642c.html b/tests/testdata/7b8675b5b8a89b52eaa2a91e1e8c08b10242642c.html
@@ -0,0 +1,11 @@
+<!DOCTYPE html>
+<html lang=en>
+  <meta charset=utf-8>
+  <meta name=viewport content="initial-scale=1, minimum-scale=1, width=device-width">
+  <title>Error 403 (Forbidden)!!1</title>
+  <style>
+    *{margin:0;padding:0}html,code{font:15px/22px arial,sans-serif}html{background:#fff;color:#222;padding:15px}body{margin:7% auto 0;max-width:390px;min-height:180px;padding:30px 0 15px}* > body{background:url(//www.google.com/images/errors/robot.png) 100% 5px no-repeat;padding-right:205px}p{margin:11px 0 22px;overflow:hidden}ins{color:#777;text-decoration:none}a img{border:0}@media screen and (max-width:772px){body{background:none;margin-top:0;max-width:none;padding-right:0}}#logo{background:url(//www.google.com/images/branding/googlelogo/1x/googlelogo_color_150x54dp.png) no-repeat;margin-left:-5px}@media only screen and (min-resolution:192dpi){#logo{background:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png) no-repeat 0% 0%/100% 100%;-moz-border-image:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png) 0}}@media only screen and (-webkit-min-device-pixel-ratio:2){#logo{background:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png) no-repeat;-webkit-background-size:100% 100%}}#logo{display:inline-block;height:54px;width:150px}
+  </style>
+  <a href=//www.google.com/><span id=logo aria-label=Google></span></a>
+  <p><b>403.</b> <ins>That’s an error.</ins>
+  <p>Your client does not have permission to get URL <code>/books/v1/volumes</code> from this server.  <ins>That’s all we know.</ins>
diff --git a/tests/testdata/7b8675b5b8a89b52eaa2a91e1e8c08b10242642c.json b/tests/testdata/7b8675b5b8a89b52eaa2a91e1e8c08b10242642c.json
@@ -0,0 +1,12 @@
+{
+	"encoding": "UTF-8",
+	"headers": {
+		"alt-svc": "h3=\":443\"; ma=2592000,h3-29=\":443\"; ma=2592000",
+		"content-length": "1595",
+		"content-type": "text/html; charset=UTF-8",
+		"date": "Thu, 12 Dec 2024 10:12:11 GMT",
+		"referrer-policy": "no-referrer"
+	},
+	"status_code": 403,
+	"url": "https://www.googleapis.com/books/v1/volumes?q=isbn:9788021087798"
+}
diff --git a/tests/testdata/cabe52f3d12d2b279e7f745d9d6ba70e2085782b.html b/tests/testdata/cabe52f3d12d2b279e7f745d9d6ba70e2085782b.html
@@ -0,0 +1 @@
+[{"key":"ZIMS77FJ","version":0,"itemType":"book","tags":[{"tag":"Jesus Christ","type":1},{"tag":"Art","type":1},{"tag":"Veronica","type":1},{"tag":"Art","type":1},{"tag":"Jesus Christ","type":1},{"tag":"Veronica","type":1},{"tag":"Veil of Veronica in art","type":1},{"tag":"Veil of Veronica in art","type":1},{"tag":"Art","type":1}],"ISBN":["978-80-210-8779-8"],"title":"The European fortune of the Roman Veronica in the Middle Ages","numPages":"303","series":"Convivium (Brno, Czech Republic). Supplementum","seriesNumber":"2017","callNumber":"N8050 .E88 2017","extra":"OCLC: on1021182894","place":"Turnhout","publisher":"Brepols","date":"2017","libraryCatalog":"Library of Congress ISBN","accessDate":"2024-12-12","editor":[["Amanda C.","Murphy"],["Herbert L.","Kessler"],["Marco","Petoletti"],["Eamon","Duffy"],["Guido","Milanese"],["Veronika","Tvrzníková"]],"oclc":"on1021182894","source":["Zotero","Library of Congress ISBN"],"url":"https://www.worldcat.org/title/on1021182894"}]
diff --git a/tests/testdata/cabe52f3d12d2b279e7f745d9d6ba70e2085782b.json b/tests/testdata/cabe52f3d12d2b279e7f745d9d6ba70e2085782b.json
@@ -0,0 +1,36 @@
+{
+	"encoding": "utf-8",
+	"headers": {
+		"accept-ranges": "bytes",
+		"access-control-allow-headers": "accept, content-type, content-length, cache-control, accept-language, api-user-agent, if-match, if-modified-since, if-none-match, dnt, accept-encoding",
+		"access-control-allow-methods": "GET,HEAD",
+		"access-control-allow-origin": "*",
+		"access-control-expose-headers": "etag",
+		"age": "1",
+		"cache-control": "private, max-age=0, s-maxage=0, must-revalidate",
+		"content-encoding": "gzip",
+		"content-length": "536",
+		"content-location": "https://en.wikipedia.org/api/rest_v1/data/citation/mediawiki/978-80-210-8779-8",
+		"content-security-policy": "default-src 'none'; frame-ancestors 'none'",
+		"content-type": "application/json; charset=utf-8",
+		"date": "Thu, 12 Dec 2024 10:12:12 GMT",
+		"nel": "{ \"report_to\": \"wm_nel\", \"max_age\": 604800, \"failure_fraction\": 0.05, \"success_fraction\": 0.0}",
+		"referrer-policy": "origin-when-cross-origin",
+		"report-to": "{ \"group\": \"wm_nel\", \"max_age\": 604800, \"endpoints\": [{ \"url\": \"https://intake-logging.wikimedia.org/v1/events?stream=w3c.reportingapi.network_error&schema_uri=/w3c/reportingapi/network_error/1.0.0\" }] }",
+		"server": "restbase1032",
+		"server-timing": "cache;desc=\"pass\", host;desc=\"cp3066\"",
+		"set-cookie": "WMF-Last-Access=12-Dec-2024;Path=/;HttpOnly;secure;Expires=Mon, 13 Jan 2025 00:00:00 GMT, WMF-Last-Access-Global=12-Dec-2024;Path=/;Domain=.wikipedia.org;HttpOnly;secure;Expires=Mon, 13 Jan 2025 00:00:00 GMT, GeoIP=IR:09:Mashhad:36.30:59.59:v4; Path=/; secure; Domain=.wikipedia.org, NetworkProbeLimit=0.001;Path=/;Secure;SameSite=Lax;Max-Age=3600",
+		"strict-transport-security": "max-age=106384710; includeSubDomains; preload",
+		"vary": "Accept-Encoding",
+		"x-cache": "cp3066 miss, cp3066 pass",
+		"x-cache-status": "pass",
+		"x-client-ip": "31.14.150.2",
+		"x-content-security-policy": "default-src 'none'; frame-ancestors 'none'",
+		"x-content-type-options": "nosniff",
+		"x-frame-options": "SAMEORIGIN",
+		"x-webkit-csp": "default-src 'none'; frame-ancestors 'none'",
+		"x-xss-protection": "1; mode=block"
+	},
+	"status_code": 200,
+	"url": "https://en.wikipedia.org/api/rest_v1/data/citation/mediawiki/978-80-210-8779-8"
+}
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		[{"key":"ZIMS77FJ","version":0,"itemType":"book","tags":[{"tag":"Jesus Christ","type":1},{"tag":"Art","type":1},{"tag":"Veronica","type":1},{"tag":"Art","type":1},{"tag":"Jesus Christ","type":1},{"tag":"Veronica","type":1},{"tag":"Veil of Veronica in art","type":1},{"tag":"Veil of Veronica in art","type":1},{"tag":"Art","type":1}],"ISBN":["978-80-210-8779-8"],"title":"The European fortune of the Roman Veronica in the Middle Ages","numPages":"303","series":"Convivium (Brno, Czech Republic). Supplementum","seriesNumber":"2017","callNumber":"N8050 .E88 2017","extra":"OCLC: on1021182894","place":"Turnhout","publisher":"Brepols","date":"2017","libraryCatalog":"Library of Congress ISBN","accessDate":"2024-12-12","editor":[["Amanda C.","Murphy"],["Herbert L.","Kessler"],["Marco","Petoletti"],["Eamon","Duffy"],["Guido","Milanese"],["Veronika","Tvrzníková"]],"oclc":"on1021182894","source":["Zotero","Library of Congress ISBN"],"url":"https://www.worldcat.org/title/on1021182894"}]