diff options
Diffstat (limited to 'extra')
| -rwxr-xr-x | extra/bootstrap_bots.sh | 25 | ||||
| -rw-r--r-- | extra/elasticsearch/changelog_schema.json | 39 | ||||
| -rw-r--r-- | extra/elasticsearch/container_schema.json | 74 | ||||
| -rw-r--r-- | extra/elasticsearch/release_schema.json | 62 | ||||
| -rw-r--r-- | extra/journal_metadata/.gitignore | 2 | ||||
| -rw-r--r-- | extra/journal_metadata/README.md | 71 | ||||
| -rw-r--r-- | extra/journal_metadata/data/.gitignore | 3 | ||||
| -rwxr-xr-x | extra/journal_metadata/data/fetch.sh | 38 | ||||
| -rwxr-xr-x | extra/journal_metadata/parse_merge_metadata.py | 398 |
9 files changed, 690 insertions, 22 deletions
diff --git a/extra/bootstrap_bots.sh b/extra/bootstrap_bots.sh new file mode 100755 index 00000000..7be148b2 --- /dev/null +++ b/extra/bootstrap_bots.sh @@ -0,0 +1,25 @@ +#!/bin/bash + +# Run this script from the ../rust/ directory, only once. + +CMD_PATH="./target/debug" + +$CMD_PATH/fatcat-auth create-editor --admin --bot crossref-bot > /dev/null +$CMD_PATH/fatcat-auth create-editor --admin --bot pubmed-bot > /dev/null +$CMD_PATH/fatcat-auth create-editor --admin --bot datacite-bot > /dev/null +$CMD_PATH/fatcat-auth create-editor --admin --bot orcid-bot > /dev/null +$CMD_PATH/fatcat-auth create-editor --admin --bot journal-metadata-bot > /dev/null +$CMD_PATH/fatcat-auth create-editor --admin --bot sandcrawler-bot > /dev/null + +echo -n "FATCAT_AUTH_WORKER_CROSSREF=" +$CMD_PATH/fatcat-auth create-token `$CMD_PATH/fatcat-auth list-editors | grep crossref-bot | cut -f1` +echo -n "FATCAT_AUTH_WORKER_PUBMED=" +$CMD_PATH/fatcat-auth create-token `$CMD_PATH/fatcat-auth list-editors | grep pubmed-bot | cut -f1` +echo -n "FATCAT_AUTH_WORKER_DATACITE=" +$CMD_PATH/fatcat-auth create-token `$CMD_PATH/fatcat-auth list-editors | grep datacite-bot | cut -f1` +echo -n "FATCAT_AUTH_WORKER_ORCID=" +$CMD_PATH/fatcat-auth create-token `$CMD_PATH/fatcat-auth list-editors | grep orcid-bot | cut -f1` +echo -n "FATCAT_AUTH_WORKER_JOURNAL_METADATA=" +$CMD_PATH/fatcat-auth create-token `$CMD_PATH/fatcat-auth list-editors | grep journal-metadata-bot | cut -f1` +echo -n "FATCAT_AUTH_SANDCRAWLER=" +$CMD_PATH/fatcat-auth create-token `$CMD_PATH/fatcat-auth list-editors | grep sandcrawler-bot | cut -f1` diff --git a/extra/elasticsearch/changelog_schema.json b/extra/elasticsearch/changelog_schema.json new file mode 100644 index 00000000..7a7ec90c --- /dev/null +++ b/extra/elasticsearch/changelog_schema.json @@ -0,0 +1,39 @@ +{ +"settings": { + "index": { + "analysis": { + "analyzer": { + "default": { + "type": "custom", + "tokenizer": "standard", + "filter": [ "lowercase", "asciifolding" ] + } + } + } + } +}, +"mappings": { + "changelog": { + "properties": { + "index": { "type": "integer" }, + "editgorup_id": { "type": "keyword" }, + "timestamp": { "type": "datetime" }, + "username": { "type": "keyword" }, + "is_bot": { "type": "boolean" }, + "is_admin": { "type": "boolean" }, + "agent": { "type": "keyword" }, + "containers": { "type": "integer" }, + "creators": { "type": "integer" }, + "files": { "type": "integer" }, + "filessets": { "type": "integer" }, + "webcaptures": { "type": "integer" }, + "releases": { "type": "integer" }, + "works": { "type": "integer" }, + "created": { "type": "integer" }, + "updated": { "type": "integer" }, + "deleted": { "type": "integer" }, + "total": { "type": "integer" } + } + } +} +} diff --git a/extra/elasticsearch/container_schema.json b/extra/elasticsearch/container_schema.json new file mode 100644 index 00000000..83791ab8 --- /dev/null +++ b/extra/elasticsearch/container_schema.json @@ -0,0 +1,74 @@ +{ +"settings": { + "index": { + "analysis": { + "analyzer": { + "default": { + "type": "custom", + "tokenizer": "standard", + "filter": [ "lowercase", "asciifolding" ] + }, + "textIcu": { + "type": "custom", + "tokenizer": "icu_tokenizer", + "char_filter": [ "icu_normalizer" ], + "filter": [ "icu_folding" ] + }, + "textIcuSearch": { + "type": "custom", + "tokenizer": "icu_tokenizer", + "char_filter": [ "icu_normalizer" ], + "filter": [ "icu_folding" ] + } + } + } + } +}, +"mappings": { + "container": { + "properties": { + "ident": { "type": "keyword" }, + "state": { "type": "keyword" }, + "revision": { "type": "keyword" }, + "name": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" }, + "publisher": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" }, + "container_type": { "type": "keyword" }, + "wikidata_qid": { "type": "keyword" }, + "issnl": { "type": "keyword" }, + "region": { "type": "keyword" }, + "nation": { "type": "keyword" }, + "discipline": { "type": "keyword" }, + "languages": { "type": "keyword" }, + "mimetypes": { "type": "keyword" }, + "first_year": { "type": "integer" }, + "last_year": { "type": "integer" }, + + "in_doaj": { "type": "boolean" }, + "in_road": { "type": "boolean" }, + "in_doi": { "type": "boolean" }, + "in_doaj_works": { "type": "boolean" }, + "in_sherpa_romeo":{ "type": "boolean" }, + "is_oa": { "type": "boolean" }, + "is_longtail_oa": { "type": "boolean" }, + "any_kbart": { "type": "boolean" }, + "any_jstor": { "type": "boolean" }, + "any_sim": { "type": "boolean" }, + "ia_homepage_status": { "type": "boolean" }, + + "releases_total": { "type": "integer" }, + "releases_kbart": { "type": "integer" }, + "releases_ia": { "type": "integer" }, + "releases_sim": { "type": "integer" }, + "releases_shadow": { "type": "integer" }, + "releases_any_file": { "type": "integer" }, + "releases_any_fileset": { "type": "integer" }, + "releases_any_webcapture": { "type": "integer" }, + + "year": { "type": "alias", "path": "first_year" }, + "type": { "type": "alias", "path": "container_type" }, + "oa": { "type": "alias", "path": "is_oa" }, + "longtail": { "type": "alias", "path": "is_longtail_oa" } + } + } +} +} diff --git a/extra/elasticsearch/release_schema.json b/extra/elasticsearch/release_schema.json index c9b77301..4cfe0894 100644 --- a/extra/elasticsearch/release_schema.json +++ b/extra/elasticsearch/release_schema.json @@ -28,41 +28,59 @@ "release": { "properties": { "ident": { "type": "keyword" }, + "state": { "type": "keyword" }, "revision": { "type": "keyword" }, "title": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" }, - "author": { "type": "alias", "path": "contrib_names" }, - "journal": { "type": "alias", "path": "container_name" }, - "date": { "type": "alias", "path": "release_date" }, - "year": { "type": "alias", "path": "release_year" }, - "issn": { "type": "alias", "path": "container_issnl" }, - "oa": { "type": "alias", "path": "container_is_oa" }, - "longtail": { "type": "alias", "path": "container_is_longtail_oa" }, + "original_title": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" }, "release_date": { "type": "date" }, "release_year": { "type": "integer" }, "release_type": { "type": "keyword" }, "release_status": { "type": "keyword" }, - "language": { "type": "keyword" }, - "doi": { "type": "keyword" }, - "pmid": { "type": "keyword" }, - "pmcid": { "type": "keyword" }, - "isbn13": { "type": "keyword" }, - "core_id": { "type": "keyword" }, - "wikidata_qid": { "type": "keyword" }, + "language": { "type": "keyword" }, + "doi": { "type": "keyword" }, + "pmid": { "type": "keyword" }, + "pmcid": { "type": "keyword" }, + "isbn13": { "type": "keyword" }, + "wikidata_qid": { "type": "keyword" }, + "core_id": { "type": "keyword" }, + "axiv_id": { "type": "keyword" }, + "jstor_id": { "type": "keyword" }, + "license": { "type": "keyword" }, "publisher": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" }, "container_name": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" }, "container_issnl": { "type": "keyword" }, - "container_is_oa": { "type": "boolean" }, - "container_is_longtail_oa": { "type": "boolean" }, + "container_type": { "type": "keyword" }, "contrib_count": { "type": "integer" }, - "contrib_names": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" }, + "contrib_names": { "type": "text", "index": true, "analyzer": "textIcu", "search_analyzer":"textIcuSearch" }, "ref_count": { "type": "integer" }, "file_count": { "type": "integer" }, - "file_pdf_url": { "type": "keyword" }, - "file_in_webarchive": { "type": "boolean" }, - "file_in_ia": { "type": "boolean" }, + "fileset_count": { "type": "integer" }, + "webcapture_count": { "type": "integer" }, "any_abstract": { "type": "boolean" }, - "is_kept": { "type": "boolean" }, - "in_shadow": { "type": "boolean" } + + "best_pdf_url": { "type": "keyword" }, + "ia_pdf_url": { "type": "keyword" }, + "is_oa": { "type": "boolean" }, + "is_longtail_oa": { "type": "boolean" }, + "is_preserved": { "type": "boolean" }, + "in_kbart": { "type": "boolean" }, + "in_jstor": { "type": "boolean" }, + "in_dweb": { "type": "boolean" }, + "in_web": { "type": "boolean" }, + "in_ia": { "type": "boolean" }, + "in_sim": { "type": "boolean" }, + "in_shadows": { "type": "boolean" }, + + "author": { "type": "alias", "path": "contrib_names" }, + "journal": { "type": "alias", "path": "container_name" }, + "date": { "type": "alias", "path": "release_date" }, + "year": { "type": "alias", "path": "release_year" }, + "issn": { "type": "alias", "path": "container_issnl" }, + "oa": { "type": "alias", "path": "is_oa" }, + "longtail": { "type": "alias", "path": "is_longtail_oa" }, + "lang": { "type": "alias", "path": "language" }, + "file_pdf_url": { "type": "alias", "path": "best_pdf_url" }, + "is_kept": { "type": "alias", "path": "in_kbart" } } } } diff --git a/extra/journal_metadata/.gitignore b/extra/journal_metadata/.gitignore new file mode 100644 index 00000000..15dbcfda --- /dev/null +++ b/extra/journal_metadata/.gitignore @@ -0,0 +1,2 @@ +*.json +*.json.gz diff --git a/extra/journal_metadata/README.md b/extra/journal_metadata/README.md new file mode 100644 index 00000000..61dbc6b0 --- /dev/null +++ b/extra/journal_metadata/README.md @@ -0,0 +1,71 @@ + +This folder contains scripts to merge journal metadat from multiple sources and +provide a snapshot for bulk importing into fatcat. + +Specific bots will probably be needed to do continous updates; that's out of +scope for this first import. + + +## Sources + +The `./data/fetch.sh` script will fetch mirrored snapshots of all these +datasets. + +A few sources of normalization/mappings: + +- ISSN-L (from ISSN org) + - Original: + - Snapshot: <https://archive.org/download/issn_issnl_mappings/20180216.ISSN-to-ISSN-L.txt> +- ISO 639-1 language codes: https://datahub.io/core/language-codes +- ISO 3166-1 alpha-2 nation codes + +In order of precedence (first higher than later): + +- NCBI Entrez (Pubmed) + - Original: <ftp://ftp.ncbi.nlm.nih.gov/pubmed/J_Entrez.txt> + - Snapshot: <https://archive.org/download/ncbi-entrez-2019/J_Entrez.txt> +- DOAJ + - Original: <https://doaj.org/csv> + - Snapshot: <https://archive.org/download/doaj_bulk_metadata_2019/doaj_20190124.csv> +- ROAD + - Original: <http://road.issn.org/en/contenu/download-road-records> + - Snapshot: <https://archive.org/download/road-issn-2018/2018-01-24/export-issn.zip> +- SHERPA/ROMEO + - Original: <http://www.sherpa.ac.uk/downloads/journal-title-issn-urls.php> (requires reg) + - Mirror: <http://www.moreo.info/?csv=romeo-journals.csv> + - Snapshot: +- Norwegian Registry + - Original: <https://dbh.nsd.uib.no/publiseringskanaler/AlltidFerskListe> + - Snapshot: <https://archive.org/download/norwegian_register_journals> +- Wikidata (TODO: Journal-level not title-level) + - Original: <http://uri.gbv.de/wikicite/20180903/> + - Snapshot: <https://archive.org/download/wikicite-biblio-data-20180903> +- KBART reports: LOCKSS, CLOCKSS, Portico + - Original: (multiple, see README in IA item) + - Snapshot: <https://archive.org/download/keepers_reports_201901> +- JSTOR + - Original: <https://support.jstor.org/hc/en-us/articles/115007466248-JSTOR-title-lists> + - Snapshot: <KBART jstor_all-archive-titles.txt> +- Crossref title list (not DOIs) + - Original: <https://wwwold.crossref.org/titlelist/titleFile.csv> + - Snapshot: <https://archive.org/download/crossref_doi_titles> +- IA SIM Microfilm catalog + - Original: <https://archive.org/download/SerialsOnMicrofilmCollection/MASTER%20TITLE_METADATA_LIST_20171019.xlsx> +- IA homepage crawl attempts + +The SHERPA/ROMEO content comes from the list helpfully munged by moreo.info. + +General form here is to build a huge python dict in memory, keyed by the +ISSN-L, then write out to disk as JSON. Then the journal-metadata importer +takes a subset of fields and inserts to fatcat. Lastly, the elasticsearch +transformer takes a subset/combination of + +## Python Helpers/Libraries + +- ftfy +- pycountry + +Debian: + + sudo apt install python3-pycountry + sudo pip3 install ftfy diff --git a/extra/journal_metadata/data/.gitignore b/extra/journal_metadata/data/.gitignore new file mode 100644 index 00000000..c3f104a6 --- /dev/null +++ b/extra/journal_metadata/data/.gitignore @@ -0,0 +1,3 @@ +* +!.gitignore +!fetch.sh diff --git a/extra/journal_metadata/data/fetch.sh b/extra/journal_metadata/data/fetch.sh new file mode 100755 index 00000000..b087d864 --- /dev/null +++ b/extra/journal_metadata/data/fetch.sh @@ -0,0 +1,38 @@ +#!/bin/bash + +set -eu + +#wget -c https://archive.org/download/road-issn-2018/2018-01-24/export-issn.zip -O road-2018-01-24-export-issn.zip +#unzip -n road-2018-01-24-export-issn.zip +wget -c https://archive.org/download/road-issn-2018/road-2018-01-24.tsv + +wget -c https://archive.org/download/doaj_bulk_metadata_2019/doaj_20190124.csv + +wget -c https://archive.org/download/issn_issnl_mappings/20181203.ISSN-to-ISSN-L.txt + +wget -c https://archive.org/download/crossref_doi_titles/doi_titles_file_2019-01-24.csv + +#wget -c https://archive.org/download/ncbi-entrez-2019/J_Entrez.txt -O ncbi-entrez-2019.txt + +wget -c https://archive.org/download/moreo.info-2018-12-20/romeo-journals.csv +wget -c https://archive.org/download/moreo.info-2018-12-20/romeo-policies.csv +wget -c https://archive.org/download/moreo.info-2018-12-20/entrez-journals.csv + +wget -c https://archive.org/download/doaj_bulk_metadata_2019/doaj_20190124.csv + +wget -c https://archive.org/download/keepers_reports_201901/jstor_all-archive-titles.txt +wget -c https://archive.org/download/keepers_reports_201901/JSTOR_Global_AllCurrentJournalTitles_2019-01-07.txt +wget -c https://archive.org/download/keepers_reports_201901/JSTOR_Global_EarlyJournalContent_2017-06-08.txt +wget -c https://archive.org/download/keepers_reports_201901/kbart_CLOCKSS.txt +wget -c https://archive.org/download/keepers_reports_201901/kbart_LOCKSS.txt +wget -c https://archive.org/download/keepers_reports_201901/Portico_Holding_KBart.txt + +wget -c https://archive.org/download/ia_journal_metadata_explore_2018-04-05/journal_homepage_results.partial.tsv + +#wget -c https://archive.org/download/SerialsOnMicrofilmCollection/MASTER%20TITLE_METADATA_LIST_20171019.xlsx +wget -c https://archive.org/download/SerialsOnMicrofilmCollection/MASTER%20TITLE_METADATA_LIST_20171019.converted.csv + +wget -c https://archive.org/download/norwegian_register_journals/2018-03-02%20Norwegian%20Register%20for%20Scientific%20Journals%20and%20Series.csv + +#wget -c https://archive.org/download/szczepanski-oa-journal-list-2018/Jan-Szczepanski-Open-Access-Journals-2018_0.docx +#wget -c https://archive.org/download/szczepanski-oa-journal-list-2018/Jan-Szczepanski-Open-Access-Journals-2018_0.converted.csv diff --git a/extra/journal_metadata/parse_merge_metadata.py b/extra/journal_metadata/parse_merge_metadata.py new file mode 100755 index 00000000..c9909a8e --- /dev/null +++ b/extra/journal_metadata/parse_merge_metadata.py @@ -0,0 +1,398 @@ +#!/usr/bin/env python3 + +import sys, csv, json +import ftfy +import pycountry + +ISSNL_FILE = 'data/20181203.ISSN-to-ISSN-L.txt' + +ENTREZ_FILE = 'data/entrez-journals.csv' +ROAD_FILE = 'data/road-2018-01-24.tsv' +ROAD_DATE = '2018-01-24' +DOAJ_FILE = 'data/doaj_20190124.csv' +DOAJ_DATE = '2019-01-24' +CROSSREF_FILE = 'data/doi_titles_file_2019-01-24.csv' +SHERPA_ROMEO_JOURNAL_FILE = 'data/romeo-journals.csv' +SHERPA_ROMEO_POLICY_FILE = 'data/romeo-policies.csv' +NORWEGIAN_FILE = 'data/2018-03-02 Norwegian Register for Scientific Journals and Series.csv' +NORWEGIAN_DATE = '2018-03-02' +LOCKSS_FILE = 'data/kbart_LOCKSS.txt' +CLOCKSS_FILE = 'data/kbart_CLOCKSS.txt' +PORTICO_FILE = 'data/Portico_Holding_KBart.txt' +JSTOR_FILE = 'data/jstor_all-archive-titles.txt' +SIM_FILE = 'data/MASTER TITLE_METADATA_LIST_20171019.converted.csv' +IA_CRAWL_FILE = 'data/journal_homepage_results.partial.tsv' + + +class Munger(): + """ + Top-level fields we'd like to fill in if possible: + + issnp: string + issne: string + first_year: year (integer) + last_year: if publishing has stopped + languages: array of ISO codes; first is the "primary" language + nation: ISO shortcode of nation published from + url: homepage + abbrev: string + default_license: slug + original_name: native name (if name is translated) + platform: hosting platform: OJS, wordpress, scielo, etc + mimetypes: array of strings (eg, 'application/pdf', 'text/html') + aliases: array of "also known as" + + Lower priority (TODO/later): + coden: string + oclc_id: string (lookup?) + lccn_id: string (lookup?) + dblb_id: string + region: TODO: continent/world-region + discipline: TODO: highest-level subject; "life science", "humanities", etc + field: TODO: narrower description of field + subjects: TODO? + + TODO: more ftfy? + TODO: remove surrounding quotes + TODO: null ISSN-L? + TODO: sherpa OA: 'Paid OA options' or 'All journals OA' + TODO: mailto: in urls + TODO: empty gaps (sim) + """ + + def __init__(self): + self.data = dict() + with open(ISSNL_FILE, 'r') as f: + self.read_issn_map_file(f) + + def run(self, out_path): + self.load_road(ROAD_FILE) + self.load_doaj(DOAJ_FILE) + self.load_crossref(CROSSREF_FILE) + self.load_norwegian(NORWEGIAN_FILE) + self.load_sherpa_romeo(SHERPA_ROMEO_JOURNAL_FILE, SHERPA_ROMEO_POLICY_FILE) + self.load_kbart('lockss', LOCKSS_FILE) + self.load_kbart('clockss', CLOCKSS_FILE) + self.load_kbart('portico', PORTICO_FILE) + self.load_kbart('jstor', JSTOR_FILE) + self.load_entrez(ENTREZ_FILE) + self.load_sim(SIM_FILE) + self.load_homepage_crawl(IA_CRAWL_FILE) + self.summarize() + self.dump(out_path) + print("Done!") + + def dump(self, out_path): + print("#### Dumping to {}".format(out_path)) + with open(out_path, 'w') as out: + for issnl in self.data: + out.write(json.dumps(self.data[issnl]) + "\n") + + def summarize(self): + print("##### Loaded {} unique entries".format(len(self.data))) + + def read_issn_map_file(self, issn_map_file): + print("##### Loading ISSN map file...") + self._issn_issnl_map = dict() + for line in issn_map_file: + if line.startswith("ISSN") or len(line) == 0: + continue + (issn, issnl) = line.split()[0:2] + self._issn_issnl_map[issn] = issnl + # double mapping makes lookups easy + self._issn_issnl_map[issnl] = issnl + print("Got {} ISSN-L mappings.".format(len(self._issn_issnl_map))) + + def issn2issnl(self, issn): + if issn is None: + return None + return self._issn_issnl_map.get(issn) + + def add_issn(self, raw_issn=None, issne=None, issnp=None, name=None, publisher=None): + # do ISSN => ISSN-L mappings for any raw ISSNs + lookup = raw_issn or issne or issnp + lookup = lookup.strip() + if not (len(lookup) == 9 and lookup[4] == '-'): + print(lookup) + print(len(lookup)) + print(lookup[4]) + assert len(lookup) == 9 and lookup[4] == '-' + issnl = self.issn2issnl(lookup.upper()) + # lookup ISSN-Ls in data (or create one) + if not issnl in self.data: + self.data[issnl] = dict(issnl=issnl) + d = self.data[issnl] + # if name/publisher not set, do so + if name and not 'name' in d: + self.data[issnl]['name'] = ftfy.fix_text(name).strip() + if publisher and not 'publisher' in d: + self.data[issnl]['publisher'] = ftfy.fix_text(publisher).strip() + if issne and not 'issne' in d: + self.data[issnl]['issne'] = issne + if issnp and not 'issnp' in d: + self.data[issnl]['issnp'] = issnp + # always return ISSN-L + return issnl + + def load_entrez(self, path): + print("##### Loading Entrez...") + # JrId,JournalTitle,MedAbbr,"ISSN (Print)","ISSN (Online)",IsoAbbr,NlmId + reader = csv.DictReader(open(path)) + skipped = 0 + count = 0 + for row in reader: + if not (row.get('ISSN (Online)') or row.get('ISSN (Print)')): + skipped += 1 + continue + issnl = self.add_issn( + issne=row.get('ISSN (Online)'), + issnp=row.get('ISSN (Print)'), + name=row['JournalTitle'], + ) + count += 1 + print("Matched {}".format(count)) + print("Skipped {} for not having ISSNs".format(skipped)) + + def load_road(self, path): + print("##### Loading ROAD...") + reader = csv.DictReader(open(path), delimiter='\t', + fieldnames=("ISSN", "ISSN-L", "Short Title", "Title", "Publisher", "URL1", "URL2", "Region", "Lang1", "Lang2") + ) + count = 0 + for row in reader: + issnl = self.add_issn( + raw_issn=row['ISSN-L'], + name=row['Short Title'], + publisher=row['Publisher'], + ) + count += 1 + d = self.data[issnl] + if row['URL1'] and not 'url' in d: + self.data[issnl]['url'] = row['URL1'] + # TODO: region mapping: "Europe and North America" + # TODO: lang mapping: already alpha-3 + self.data[issnl]['road'] = dict(as_of=ROAD_DATE) + print("Matched {}".format(count)) + + def load_doaj(self, path): + print("##### Loading DOAJ...") + #Journal title Journal URL Alternative title ISSN-print ISSN-electronic Publisher Society or institution Platform, host or aggregator Country of publisher Journal article processing charges (APCs) ... Deposit policy directory Author holds copyright without restrictions Copyright information URL Author holds publishing rights without restrictions Publishing rights information URL DOAJ Seal Tick: Accepted after March 2014 Added on Date Subjects ISSN-L + reader = csv.DictReader(open(path)) + count = 0 + for row in reader: + issnl = self.add_issn( + issnp=row['Journal ISSN (print version)'], + issne=row['Journal EISSN (online version)'], + name=row['Journal title'], + publisher=row['Publisher'], + ) + count += 1 + d = self.data[issnl] + doaj = dict(as_of=DOAJ_DATE) + # TODO: work_level: bool (are work-level publications deposited with DOAJ?) + # TODO: archiving: array, can include 'library' or 'other' + + if row['Platform, host or aggregator']: + # TODO: mapping here? + self.data[issnl]['platform'] = row['Platform, host or aggregator'] + if row['DOAJ Seal']: + doaj['seal'] = {"no": False, "yes": True}[row['DOAJ Seal'].lower()] + if row['Country of publisher']: + # TODO: country mapping + self.data[issnl]['country'] = row['Country of publisher'] + # TODO: Subjects + self.data[issnl]['doaj'] = doaj + print("Matched {}".format(count)) + + def load_sherpa_romeo(self, journal_path, policy_path): + # first load policies + print("##### Loading SHERPA/ROMEO policies...") + #RoMEO Record ID,Publisher,Policy Heading,Country,RoMEO colour,Published Permission,Published Restrictions,Published Max embargo,Accepted Prmission,Accepted Restrictions,Accepted Max embargo,Submitted Permission,Submitted Restrictions,Submitted Max embargo,Open Access Publishing,Record Status,Updated + policies = dict() + fixed_policy_file = ftfy.fix_file(open(policy_path, 'rb')) + policy_reader = csv.DictReader(fixed_policy_file) + for row in policy_reader: + policies[row['RoMEO Record ID']] = row + print("##### Loading SHERPA/ROMEO journal metadata...") + #Journal Title,ISSN,ESSN,URL,RoMEO Record ID,Updated + # super mangled :( + raw_file = open(journal_path, 'rb').read().decode(errors='replace') + fixed_file = ftfy.fix_text(raw_file) + reader = csv.DictReader(fixed_file.split('\n')) + count = 0 + for row in reader: + #row['Journal Title'] = row.pop('\ufeffJournal Title') + row.update(policies[row['RoMEO Record ID']]) + issnl = self.add_issn( + issnp=row['ISSN'], + issne=row['ESSN'], + name=row['Journal Title'], + publisher=row['Publisher'], + ) + count += 1 + d = self.data[issnl] + sherpa_romeo = dict() + if row['RoMEO colour']: + sherpa_romeo['color'] = row['RoMEO colour'] + if row['Open Access Publishing']: + # TODO: boolean? + sherpa_romeo['oa'] = row['Open Access Publishing'] + if row['Country'] and not 'country' in d: + self.data[issnl]['country'] = row['Country'].lower() + self.data[issnl]['sherpa_romeo'] = sherpa_romeo + print("Matched {}".format(count)) + + def load_norwegian(self, path): + print("##### Loading Norwegian Registry...") + #pandas.read_csv(NORWEGIAN_FILE, sep=';', encoding="ISO-8859-1") + #NSD tidsskrift_id;Original title;International title;Present Level (2018);Print ISSN;Online ISSN;Open Access;NPI Scientific Field;NPI Academic Discipline;URL;Publishing Company;Publisher;Country of publication;Language;Level 2019;Level 2018;Level 2017;Level 2016;Level 2015;Level 2014;Level 2013;Level 2012;Level 2011;Level 2010;Level 2009;Level 2008;Level 2007;Level 2006;Level 2005;Level 2004;itar_id + reader = csv.DictReader(open(path, encoding="ISO-8859-1"), delimiter=";") + count = 0 + skip = 0 + for row in reader: + issnp = row['Print ISSN'] + issne = row['Online ISSN'] + if issne and len(issne.strip()) != 9: + issne = None + if issnp and len(issnp.strip()) != 9: + issnp = None + if not (issnp or issne): + skip += 1 + continue + issnl = self.add_issn( + issnp=issnp, + issne=issne, + name=row['International title'], + publisher=row['Publisher'], + ) + count += 1 + d = self.data[issnl] + norwegian = dict(as_of=NORWEGIAN_DATE) + norwegian['level'] = int(row['Present Level (2018)']) + norwegian['id'] = int(row['NSD tidsskrift_id']) + + if row['Original title'] != row['International title'] and not 'original_name' in d: + self.data[issnl]['original_name'] = row['Original title'] + if row['Country of publication'] and not 'country' in d: + # TODO: country mapping + self.data[issnl]['country'] = row['Country of publication'] + if row['Language'] and not 'language' in d: + # TODO: language mapping + self.data[issnl]['language'] = row['Language'] + self.data[issnl]['norwegian'] = norwegian + print("Skipped {} for mangled ISSN".format(skip)) + print("Matched {}".format(count)) + + def load_kbart(self, name, path): + print("##### Loading KBART file for {}...".format(name)) + #publication_title print_identifier online_identifier date_first_issue_online num_first_vol_online num_first_issue_online date_last_issue_online num_last_vol_online num_last_issue_online title_url first_author title_id embargo_info coverage_depth coverage_notes publisher_name + raw_file = open(path, 'rb').read().decode(errors='replace') + fixed_file = ftfy.fix_text(raw_file) + reader = csv.DictReader(fixed_file.split('\n'), delimiter='\t') + count = 0 + skip = 0 + for row in reader: + if not row['print_identifier'] and not row['online_identifier']: + skip += 1 + continue + issnl = self.add_issn( + issnp=row['print_identifier'], + issne=row['online_identifier'], + name=row['publication_title'], + publisher=row['publisher_name'], + ) + count += 1 + d = self.data[issnl] + if not 'kbart' in d: + self.data[issnl]['kbart'] = dict() + kbart = dict() + if row['date_first_issue_online'] and row['date_last_issue_online']: + kbart['year_span'] = [[int(row['date_first_issue_online'][:4]), int(row['date_last_issue_online'][:4])]] + self.data[issnl]['kbart'][name] = kbart + print("Skipped {} missing ISSN".format(skip)) + print("Matched {}".format(count)) + + def load_crossref(self, path): + print("##### Loading Crossref...") + #"JournalTitle","JournalID","Publisher","pissn","eissn","additionalIssns","doi","(year1)[volume1]issue1,issue2,issue3(year2)[volume2]issue4,issues5" + reader = csv.DictReader(open(path)) + count = 0 + skip = 0 + for row in reader: + if row['pissn'] and len(row['pissn']) == 8: + row['pissn'] = row['pissn'][:4] + '-' + row['pissn'][4:] + if row['eissn'] and len(row['eissn']) == 8: + row['eissn'] = row['eissn'][:4] + '-' + row['eissn'][4:] + if not (row['pissn'] or row['eissn']): + skip += 1 + continue + issnl = self.add_issn( + issnp=row['pissn'], + issne=row['eissn'], + name=row['JournalTitle'], + publisher=row['Publisher'], + ) + count += 1 + d = self.data[issnl] + crossref = dict() + if row['doi']: + crossref['doi'] = row['doi'] + self.data[issnl]['crossref'] = crossref + print("Skipped {} missing ISSN".format(skip)) + print("Matched {}".format(count)) + + def load_sim(self, path): + print("##### Loading SIM Metadata...") + #NA Pub Cat ID,Title,Publisher,ISSN,Impact Rank,Total Cities,Journal Impact Factor,Eigenfact or Score,First Volume,Last Volume,NA Gaps,"Scholarly / Peer-\n Reviewed","Peer-\n Reviewed",Pub Type,Pub Language,Subjects + reader = csv.DictReader(open(path)) + count = 0 + skip = 0 + for row in reader: + if not row['ISSN'] or row['ISSN'] == "NULL": + skip += 1 + continue + issnl = self.add_issn( + raw_issn=row['ISSN'][:9], + name=row['Title'], + publisher=row['Publisher'], + ) + count += 1 + d = self.data[issnl] + sim = dict() + sim['id'] = row['NA Pub Cat ID'] + sim['first_year'] = row['First Volume'] + sim['last_year'] = row['Last Volume'] + sim['gaps'] = row['NA Gaps'] + # TODO: 'Pub Language' + # TODO: 'Pub Type' + self.data[issnl]['sim'] = sim + print("Skipped {} missing ISSN".format(skip)) + print("Matched {}".format(count)) + + def load_homepage_crawl(self, path): + print("##### Loading IA Homepage Crawl Results...") + reader = csv.DictReader(open(path), delimiter='\t', + fieldnames=("ISSN", "first_url", "first_status", "last_status", "last_url") + ) + count = 0 + skip = 0 + for row in reader: + issnl = self.add_issn( + raw_issn=row['ISSN'], + ) + count += 1 + d = self.data[issnl] + ia = d.get('ia', dict()) + ia['homepage_status'] = int(row['last_status']) + if ia['homepage_status'] == 200: + ia['homepage_url'] = row['last_url'] + else: + ia['homepage_url'] = row['first_url'] + self.data[issnl]['ia'] = ia + print("Skipped {} missing ISSN".format(skip)) + print("Matched {}".format(count)) + +if __name__=='__main__': + munger = Munger() + munger.run(sys.argv[1]) + |