diff options
| -rw-r--r-- | extra/sitemap/README.md | 3 | ||||
| -rwxr-xr-x | extra/sitemap/work_urls_query.sh | 5 | ||||
| -rw-r--r-- | fatcat_scholar/translations/ko/LC_MESSAGES/messages.po (renamed from fatcat_scholar/translations/cs/LC_MESSAGES/messages.po) | 268 |
3 files changed, 143 insertions, 133 deletions
diff --git a/extra/sitemap/README.md b/extra/sitemap/README.md index 242378a..1e1938a 100644 --- a/extra/sitemap/README.md +++ b/extra/sitemap/README.md @@ -8,7 +8,8 @@ installed. Run these commands on a production machine. export DATE=`date --iso-8601` /srv/fatcat_scholar/src/extra/sitemap/work_urls_query.sh $DATE rm *.txt.gz - /srv/fatcat/src/extra/sitemap/generate_sitemap_indices.py + gzip sitemap-*.txt + /srv/fatcat_scholar/src/extra/sitemap/generate_sitemap_indices.py ## Background diff --git a/extra/sitemap/work_urls_query.sh b/extra/sitemap/work_urls_query.sh index c02eb74..2971f47 100755 --- a/extra/sitemap/work_urls_query.sh +++ b/extra/sitemap/work_urls_query.sh @@ -9,9 +9,8 @@ set -o pipefail # fail if part of a '|' command fails # eg, 2020-08-19 DATE="$1" -# query for specific works - -fatcat-cli search scholar "doc_type:work (fulltext.access_type:ia_file OR fulltext.access_type:wayback) (year:<1925 OR publisher_type:longtail OR publisher_type:oa)" --index-json --limit 0 \ +# query for specific works; about 8.6 million circa 2021-04-29 +fatcat-cli search scholar 'doc_type:work (fulltext.access_type:ia_file OR fulltext.access_type:wayback) (NOT biblio.arxiv_id:*) (NOT biblio.pmcid:*) (NOT biblio.publisher_type:big5) (year:<1926 OR tags:*)' --index-json --limit 0 \ | pv -l \ | jq .key -r \ | tr '_' '/' \ diff --git a/fatcat_scholar/translations/cs/LC_MESSAGES/messages.po b/fatcat_scholar/translations/ko/LC_MESSAGES/messages.po index 0aef9d3..a5df371 100644 --- a/fatcat_scholar/translations/cs/LC_MESSAGES/messages.po +++ b/fatcat_scholar/translations/ko/LC_MESSAGES/messages.po @@ -1,22 +1,22 @@ -# Czech translations for PROJECT. -# Copyright (C) 2020 ORGANIZATION +# Korean translations for PROJECT. +# Copyright (C) 2021 ORGANIZATION # This file is distributed under the same license as the PROJECT project. -# FIRST AUTHOR <EMAIL@ADDRESS>, 2020. +# FIRST AUTHOR <EMAIL@ADDRESS>, 2021. # msgid "" msgstr "" "Project-Id-Version: PROJECT VERSION\n" "Report-Msgid-Bugs-To: EMAIL@ADDRESS\n" "POT-Creation-Date: 2021-03-25 11:07-0700\n" -"PO-Revision-Date: 2020-11-02 21:52-0800\n" +"PO-Revision-Date: 2021-04-30 11:57-0700\n" "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n" -"Language-Team: cs <LL@li.org>\n" -"Language: cs\n" +"Language: ko\n" +"Language-Team: ko <LL@li.org>\n" +"Plural-Forms: nplurals=1; plural=0\n" "MIME-Version: 1.0\n" -"Content-Type: text/plain; charset=UTF-8\n" +"Content-Type: text/plain; charset=utf-8\n" "Content-Transfer-Encoding: 8bit\n" -"Plural-Forms: nplurals=3; plural=((n==1) ? 0 : (n>=2 && n<=4) ? 1 : 2)\n" -"Generated-By: Babel 2.8.0\n" +"Generated-By: Babel 2.6.0\n" #: fatcat_scholar/search.py:42 msgid "Release Date" @@ -110,8 +110,8 @@ msgstr "" #: fatcat_scholar/templates/about.html:10 #, python-format msgid "" -"See also: <a href=\"%(lang_prefix)s/help\">User Guide</a> which lists some " -"bugs and known issues" +"See also: <a href=\"%(lang_prefix)s/help\">User Guide</a> which lists " +"some bugs and known issues" msgstr "" #: fatcat_scholar/templates/about.html:14 @@ -125,9 +125,9 @@ msgstr "" #: fatcat_scholar/templates/about.html:19 msgid "" -"<b>public web content</b> as preserved in <a href=\"https://web.archive.org" -"\">The Wayback Machine</a> and <a href=\"https://archive-it.org\">Archive-" -"It</a> partner collections" +"<b>public web content</b> as preserved in <a " +"href=\"https://web.archive.org\">The Wayback Machine</a> and <a " +"href=\"https://archive-it.org\">Archive-It</a> partner collections" msgstr "" #: fatcat_scholar/templates/about.html:20 @@ -136,15 +136,16 @@ msgstr "" #: fatcat_scholar/templates/about.html:21 msgid "" -"<b>general materials</b> from <a href=\"https://archive.org\">archive.org " -"collections</a>, including collaborations with partners" +"<b>general materials</b> from <a href=\"https://archive.org\">archive.org" +" collections</a>, including collaborations with partners" msgstr "" #: fatcat_scholar/templates/about.html:24 #, python-format msgid "" -"This <a href=\"%(url)s\">2019 FORCE11 conference presentation</a> gives an " -"overview of the technical infrastructure and goals of the project overall." +"This <a href=\"%(url)s\">2019 FORCE11 conference presentation</a> gives " +"an overview of the technical infrastructure and goals of the project " +"overall." msgstr "" #: fatcat_scholar/templates/about.html:27 @@ -156,7 +157,8 @@ msgstr "" msgid "" "Metadata comes from <a href=\"https://fatcat.wiki\">fatcat.wiki</a>, an " "open\n" -"user-editable catalog of scholarly work. It should be possible to track and\n" +"user-editable catalog of scholarly work. It should be possible to track " +"and\n" "attribute the provenance of content and metadata in all cases. Please\n" "<a href=\"#contact\">contact us</a> if you have questions." msgstr "" @@ -168,9 +170,10 @@ msgstr "" #: fatcat_scholar/templates/about.html:37 msgid "" -"We intend to provide researcher access to the full corpus for text and data\n" -"mining purposes. Derived datasets may also be posted publicly for analysis, " -"for\n" +"We intend to provide researcher access to the full corpus for text and " +"data\n" +"mining purposes. Derived datasets may also be posted publicly for " +"analysis, for\n" "example a citation graph or N-gram frequencies by year. If you are " "interested\n" "or would like to see specific datasets made available, please contact us." @@ -178,10 +181,10 @@ msgstr "" #: fatcat_scholar/templates/about.html:42 msgid "" -"Currently snapshots of the full fatcat metadata corpus and upstream metadata " -"sources are uploaded periodically to the <a href=\"https://archive.org/" -"details/ia_biblio_metadata\">Bulk Bibliographic Metadata</a> collection on " -"archive.org." +"Currently snapshots of the full fatcat metadata corpus and upstream " +"metadata sources are uploaded periodically to the <a " +"href=\"https://archive.org/details/ia_biblio_metadata\">Bulk " +"Bibliographic Metadata</a> collection on archive.org." msgstr "" #: fatcat_scholar/templates/about.html:44 @@ -197,15 +200,15 @@ msgstr "" #: fatcat_scholar/templates/about.html:50 #, python-format msgid "" -"The organizational contact information for the Internet Archive is listed at " -"<a href=\"%(url)s\">%(url)s</a>." +"The organizational contact information for the Internet Archive is listed" +" at <a href=\"%(url)s\">%(url)s</a>." msgstr "" #: fatcat_scholar/templates/about.html:52 #, python-format msgid "" -"Queries about this search service and the fatcat catalog can be directed to " -"<a href=\"mailto:%(email)s\">%(email)s</a>." +"Queries about this search service and the fatcat catalog can be directed " +"to <a href=\"mailto:%(email)s\">%(email)s</a>." msgstr "" #: fatcat_scholar/templates/about.html:54 @@ -250,8 +253,8 @@ msgstr "" #: fatcat_scholar/templates/base.html:163 #, python-format msgid "" -"Other projects include %(wayback)s, %(archive_org)s, %(openlibrary)s, and " -"%(archive_it)s." +"Other projects include %(wayback)s, %(archive_org)s, %(openlibrary)s, and" +" %(archive_it)s." msgstr "" #: fatcat_scholar/templates/base.html:170 @@ -335,10 +338,10 @@ msgstr "" #: fatcat_scholar/templates/help.html:25 msgid "" "This service provides <a href=\"https://en.wikipedia.org/wiki/Full-" -"text_search\">fulltext searching</a> over research publications archived in " -"Internet Archive's various collections. It includes content from the natural " -"sciences, humanities, biomedicine, art, history, industrial research, " -"government reports, and more." +"text_search\">fulltext searching</a> over research publications archived " +"in Internet Archive's various collections. It includes content from the " +"natural sciences, humanities, biomedicine, art, history, industrial " +"research, government reports, and more." msgstr "" #: fatcat_scholar/templates/help.html:26 @@ -350,9 +353,10 @@ msgstr "" #: fatcat_scholar/templates/help.html:28 msgid "" -"In other cases, depending on search filters, results are included for which " -"there is only a bibliographic catalog entry. It may still be possible to " -"obtain access through a public library or from the publisher directly." +"In other cases, depending on search filters, results are included for " +"which there is only a bibliographic catalog entry. It may still be " +"possible to obtain access through a public library or from the publisher " +"directly." msgstr "" #: fatcat_scholar/templates/help.html:30 @@ -362,8 +366,8 @@ msgstr "" #: fatcat_scholar/templates/help.html:32 msgid "" "In addition to the basic filtering and sorting options, this search\n" -"interface also allows the use of Lucene query syntax in the search box. You " -"can\n" +"interface also allows the use of Lucene query syntax in the search box. " +"You can\n" "restrict term queries on multiple metadata fields using colon statements " "like\n" "<code>journal:Science</code>, set filters like <code>lang:de</code>, and\n" @@ -373,14 +377,14 @@ msgstr "" #: fatcat_scholar/templates/help.html:38 msgid "" "While this syntax allows for relatively complex and powerful queries, at " -"some point advanced users may run into limits on the size or complexity of " -"queries." +"some point advanced users may run into limits on the size or complexity " +"of queries." msgstr "" #: fatcat_scholar/templates/help.html:40 msgid "" -"For the time being we recommend systems like <a href=\"https://lens.org" -"\">lens.org</a> for a more powerful interface." +"For the time being we recommend systems like <a " +"href=\"https://lens.org\">lens.org</a> for a more powerful interface." msgstr "" #: fatcat_scholar/templates/help.html:43 @@ -406,9 +410,9 @@ msgstr "" #: fatcat_scholar/templates/help.html:58 msgid "" "As an experimental feature, if the search query \"looks like\" a formal " -"citation, as found in the bibliography of a research paper, the service will " -"attempt to parse the citation and do a match against our catalog of known " -"works. When this happens, any filters are ignored." +"citation, as found in the bibliography of a research paper, the service " +"will attempt to parse the citation and do a match against our catalog of " +"known works. When this happens, any filters are ignored." msgstr "" #: fatcat_scholar/templates/help.html:62 @@ -418,23 +422,24 @@ msgstr "" #: fatcat_scholar/templates/help.html:64 msgid "" "You can restrict to records where the field exists with an asterisk like " -"<code>doi:*</code>, and negate any term like <code>!type:article-journal</" -"code>." +"<code>doi:*</code>, and negate any term like <code>!type:article-" +"journal</code>." msgstr "" #: fatcat_scholar/templates/help.html:66 msgid "" -"In-depth documentation of the query syntax is available <a href=\"https://" -"www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-query-" -"string-query.html#query-string-query-notes\">from the Elasticsearch project</" -"a>." +"In-depth documentation of the query syntax is available <a " +"href=\"https://www.elastic.co/guide/en/elasticsearch/reference/current" +"/query-dsl-query-string-query.html#query-string-query-notes\">from the " +"Elasticsearch project</a>." msgstr "" #: fatcat_scholar/templates/help.html:68 msgid "" -"The complete current search document schema is available (as JSON) <a href=" -"\"https://github.com/internetarchive/fatcat-scholar/blob/master/schema/" -"scholar_fulltext.v01.json\">in the source code</a>." +"The complete current search document schema is available (as JSON) <a " +"href=\"https://github.com/internetarchive/fatcat-" +"scholar/blob/master/schema/scholar_fulltext.v01.json\">in the source " +"code</a>." msgstr "" #: fatcat_scholar/templates/help.html:105 @@ -447,22 +452,23 @@ msgstr "" #: fatcat_scholar/templates/help.html:118 msgid "" -"All Internet Archive preservation copy links have the same style and icon. " -"Content from the Wayback Machine looks like this." +"All Internet Archive preservation copy links have the same style and " +"icon. Content from the Wayback Machine looks like this." msgstr "" #: fatcat_scholar/templates/help.html:122 msgid "" -"If the preserved copy of the work is from a pre-print, author manuscript, or " -"other alternative version of the work, the access link has an indicator. You " -"can get details and view all versions by clicking on the primary title link" +"If the preserved copy of the work is from a pre-print, author manuscript," +" or other alternative version of the work, the access link has an " +"indicator. You can get details and view all versions by clicking on the " +"primary title link" msgstr "" #: fatcat_scholar/templates/help.html:126 msgid "" "Some preserved content, particularly older Public Domain works, may be " -"stored in general Internet Archive digital collections (as opposed to the " -"web archive)" +"stored in general Internet Archive digital collections (as opposed to the" +" web archive)" msgstr "" #: fatcat_scholar/templates/help.html:130 @@ -473,16 +479,16 @@ msgstr "" #: fatcat_scholar/templates/help.html:134 msgid "" -"A publisher landing page is the authoritative source for the \"version of " -"record\" of a research publication, but content is not always accessible to " -"the general public" +"A publisher landing page is the authoritative source for the \"version of" +" record\" of a research publication, but content is not always accessible" +" to the general public" msgstr "" #: fatcat_scholar/templates/help.html:138 msgid "" -"When the work is from an Open Access publication (sometimes known as \"Gold" -"\" or \"Diamond\" OA), and the publisher is expected to provide access to " -"all readers, the button has an orange \"unlocked\" icon" +"When the work is from an Open Access publication (sometimes known as " +"\"Gold\" or \"Diamond\" OA), and the publisher is expected to provide " +"access to all readers, the button has an orange \"unlocked\" icon" msgstr "" #: fatcat_scholar/templates/help.html:142 @@ -493,23 +499,24 @@ msgstr "" #: fatcat_scholar/templates/help.html:150 msgid "" -"Search results may have tag labels which provide additional context about " -"the work. For example, indexes the journal is included in, or open platform " -"technology used for publications." +"Search results may have tag labels which provide additional context about" +" the work. For example, indexes the journal is included in, or open " +"platform technology used for publications." msgstr "" #: fatcat_scholar/templates/help.html:160 msgid "" -"There are multiple released \"versions\" or \"editions\" of this work, and " -"bibliographic metadata for the \"primary\" is being shown. Click the title " -"to see other versions" +"There are multiple released \"versions\" or \"editions\" of this work, " +"and bibliographic metadata for the \"primary\" is being shown. Click the " +"title to see other versions" msgstr "" #: fatcat_scholar/templates/help.html:164 msgid "" "The primary language of this work is different from the search interface " -"language. The <a href=\"https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes" -"\">ISO two-letter language code</a> is indicated" +"language. The <a " +"href=\"https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes\">ISO two-" +"letter language code</a> is indicated" msgstr "" #: fatcat_scholar/templates/help.html:168 @@ -520,53 +527,58 @@ msgstr "" #: fatcat_scholar/templates/help.html:172 msgid "" -"Publication indexed in <a href=\"https://www.ebsco.com/open-access/" -"szczepanski-list\">Szczepanski's List of Open Access Journals</a>, which " -"implies that this is an Open Access work" +"Publication indexed in <a href=\"https://www.ebsco.com/open-access" +"/szczepanski-list\">Szczepanski's List of Open Access Journals</a>, which" +" implies that this is an Open Access work" msgstr "" #: fatcat_scholar/templates/help.html:176 msgid "" -"The work is believed to be <a href=\"https://en.wikipedia.org/wiki/" -"Open_access\">\"Open Access\"</a> for any other reason" +"The work is believed to be <a " +"href=\"https://en.wikipedia.org/wiki/Open_access\">\"Open Access\"</a> " +"for any other reason" msgstr "" #: fatcat_scholar/templates/help.html:180 msgid "" -"Published on a <a href=\"https://en.wikipedia.org/wiki/SciELO\">SciELO</a> " -"national platform" +"Published on a <a " +"href=\"https://en.wikipedia.org/wiki/SciELO\">SciELO</a> national " +"platform" msgstr "" #: fatcat_scholar/templates/help.html:184 msgid "" -"Published using <a href=\"https://en.wikipedia.org/wiki/Open_Journal_Systems" -"\">Open Journal Systems</a> software" +"Published using <a " +"href=\"https://en.wikipedia.org/wiki/Open_Journal_Systems\">Open Journal " +"Systems</a> software" msgstr "" #: fatcat_scholar/templates/help.html:188 msgid "" -"Published using <a href=\"https://en.wikipedia.org/wiki/Wordpress" -"\">WordPress</a> software" +"Published using <a " +"href=\"https://en.wikipedia.org/wiki/Wordpress\">WordPress</a> software" msgstr "" #: fatcat_scholar/templates/help.html:192 msgid "" -"Preserved and/or hosted on the <a href=\"https://en.wikipedia.org/wiki/JSTOR" -"\">JSTOR</a> digital preservation platform" +"Preserved and/or hosted on the <a " +"href=\"https://en.wikipedia.org/wiki/JSTOR\">JSTOR</a> digital " +"preservation platform" msgstr "" #: fatcat_scholar/templates/help.html:200 msgid "" "Underneath search results, and alternate version listings, are any known " -"\"persistent identifiers\" that uniquely identify the specific version of " -"the work. These are usually hyperlinks." +"\"persistent identifiers\" that uniquely identify the specific version of" +" the work. These are usually hyperlinks." msgstr "" #: fatcat_scholar/templates/help.html:210 msgid "" -"<a href=\"https://en.wikipedia.org/wiki/Digital_object_identifier\">Digital " -"Object Identifier (DOI)</a>, provides a redirect to the publisher's landing " -"page" +"<a " +"href=\"https://en.wikipedia.org/wiki/Digital_object_identifier\">Digital " +"Object Identifier (DOI)</a>, provides a redirect to the publisher's " +"landing page" msgstr "" #: fatcat_scholar/templates/help.html:214 @@ -586,8 +598,7 @@ msgid "The DBLP Computer Science Bibliography" msgstr "" #: fatcat_scholar/templates/help.html:230 -msgid "" -"Article-level identifier for works in DOAJ, particularly those with no DOI" +msgid "Article-level identifier for works in DOAJ, particularly those with no DOI" msgstr "" #: fatcat_scholar/templates/help.html:234 @@ -602,14 +613,14 @@ msgstr "" #: fatcat_scholar/templates/help.html:244 fatcat_scholar/templates/home.html:37 msgid "" -"This service is in \"alpha\". It has several bugs, experiences downtime, and " -"has not been officially announced." +"This service is in \"alpha\". It has several bugs, experiences downtime, " +"and has not been officially announced." msgstr "" #: fatcat_scholar/templates/help.html:246 fatcat_scholar/templates/home.html:39 msgid "" -"This is a new service. Metadata is being improved and features have not been " -"finalized." +"This is a new service. Metadata is being improved and features have not " +"been finalized." msgstr "" #: fatcat_scholar/templates/help.html:250 @@ -628,16 +639,16 @@ msgstr "" #: fatcat_scholar/templates/help.html:257 msgid "" -"Duplicate versions of same work. For example, different versions of the same " -"paper or dataset. We are working on basic entity-deduplication in the fatcat " -"catalog." +"Duplicate versions of same work. For example, different versions of the " +"same paper or dataset. We are working on basic entity-deduplication in " +"the fatcat catalog." msgstr "" #: fatcat_scholar/templates/help.html:258 msgid "" "Mis-matching of file content or version with work metadata. For example, " -"sometimes pre-prints or author manuscripts are incorrectly associated with " -"version-of-record metadata, or vice-versa." +"sometimes pre-prints or author manuscripts are incorrectly associated " +"with version-of-record metadata, or vice-versa." msgstr "" #: fatcat_scholar/templates/home.html:10 @@ -654,15 +665,15 @@ msgstr "" #: fatcat_scholar/templates/home.html:24 msgid "" -"This fulltext search index includes over 25 million research articles and " -"other scholarly documents preserved in the Internet Archive." +"This fulltext search index includes over 25 million research articles and" +" other scholarly documents preserved in the Internet Archive." msgstr "" #: fatcat_scholar/templates/home.html:24 msgid "" -"The collection spans from digitized copies of eighteenth century journals " -"through the latest Open Access conference proceedings and pre-prints crawled " -"from the World Wide Web." +"The collection spans from digitized copies of eighteenth century journals" +" through the latest Open Access conference proceedings and pre-prints " +"crawled from the World Wide Web." msgstr "" #: fatcat_scholar/templates/home.html:24 @@ -683,8 +694,6 @@ msgstr "" msgid "Hit" msgid_plural "Hits" msgstr[0] "" -msgstr[1] "" -msgstr[2] "" #: fatcat_scholar/templates/search.html:53 #: fatcat_scholar/templates/search.html:85 @@ -702,8 +711,8 @@ msgstr "" #: fatcat_scholar/templates/search.html:116 msgid "" -"Query parsing is currently very naive. Sometimes you can fix this problem by " -"adding quotes around terms or entire phrases." +"Query parsing is currently very naive. Sometimes you can fix this problem" +" by adding quotes around terms or entire phrases." msgstr "" #: fatcat_scholar/templates/search.html:148 @@ -817,10 +826,10 @@ msgstr "" #: fatcat_scholar/templates/search_macros.html:288 #, python-format msgid "" -"A copy of this work was available on the public web and has been preserved " -"in the Wayback Machine. The capture dates from %(capture_year)s; you can " -"also visit <a rel=\"external noopener\" href=\"%(original_url)s\">the " -"original URL</a>." +"A copy of this work was available on the public web and has been " +"preserved in the Wayback Machine. The capture dates from " +"%(capture_year)s; you can also visit <a rel=\"external noopener\" " +"href=\"%(original_url)s\">the original URL</a>." msgstr "" #: fatcat_scholar/templates/search_macros.html:290 @@ -831,8 +840,8 @@ msgstr "" #: fatcat_scholar/templates/search_macros.html:292 msgid "" -"The Internet Archive has digitized a microfilm copy of this work. It may be " -"possible to borrow a copy for reading." +"The Internet Archive has digitized a microfilm copy of this work. It may " +"be possible to borrow a copy for reading." msgstr "" #: fatcat_scholar/templates/search_macros.html:296 @@ -842,8 +851,8 @@ msgstr "" #: fatcat_scholar/templates/search_macros.html:301 msgid "" -"Note that this fulltext copy is not of the \"primary\" version of this work. " -"The version it corresponds to is:" +"Note that this fulltext copy is not of the \"primary\" version of this " +"work. The version it corresponds to is:" msgstr "" #: fatcat_scholar/templates/search_macros.html:314 @@ -853,16 +862,16 @@ msgstr "" #: fatcat_scholar/templates/search_macros.html:324 msgid "" "We don't yet know of a public preservation copy of this work. You may be " -"able to obtain a copy of this work to read from the publisher, platforms, or " -"institutional libraries." +"able to obtain a copy of this work to read from the publisher, platforms," +" or institutional libraries." msgstr "" #: fatcat_scholar/templates/search_macros.html:327 #, python-format msgid "" -"If you know of a legal, public version that we should archive, please let us " -"know via <a rel=\"noopener\" href=\"%(save_paper_now_url)s\">\"Save Paper Now" -"\"</a>." +"If you know of a legal, public version that we should archive, please let" +" us know via <a rel=\"noopener\" href=\"%(save_paper_now_url)s\">\"Save " +"Paper Now\"</a>." msgstr "" #: fatcat_scholar/templates/search_macros.html:374 @@ -916,3 +925,4 @@ msgstr "" #: fatcat_scholar/templates/search_macros.html:541 msgid "Clear Filters" msgstr "" + |