adsabs / ADSImportPipeline

Data ingest pipeline for ADS classic->ADS+
GNU General Public License v3.0
1 stars 12 forks source link

not listing full author names #169

Open romanchyla opened 6 years ago

romanchyla commented 6 years ago

example: 1980ITED...27..126S

classic shows the full name, but merger rules pick the arxiv version - surprisingly, only in the new pipeline (the old pipeline was the same)

x = read_records.readRecordsFromADSExports([('1980ITED...27..126S', 'ignore2')])  
{'JSON_fingerprint': 'ignore2',
 'bibcode': u'1980ITED...27..126S',
 'entry_date': u'1995-08-29',
 'metadata': [{'abstracts': [{'lang': u'en',
     'origin': u'STI',
     'text': u"The optical and detector properties of PbS-Si heterojunctions (HJ) are studied. The absorption of PbS films and PbS-Si HJ's have been measured by IR spectroscopy. The photosignal and noise measurem
ents of PbS-Si HJ's are outlined. HJ detectivity and its spectral response are emphasized."}],
   'arxivcategories': [],
   'authors': [{'affiliations': [u'Rensselaer Polytechnic Institute, Troy, N.Y.'],
     'emails': [],
     'name': {'native': None,
      'normalized': u'Steckl, A',
      'western': u'Steckl, A. J.'},
     'number': u'1',
     'orcid': None,
     'type': u'regular'},
    {'affiliations': [u'Rensselaer Polytechnic Institute, Troy, N.Y.'],
     'emails': [],
     'name': {'native': None,
      'normalized': u'Elabd, H',
      'western': u'Elabd, H.'},
     'number': u'2',
     'orcid': None,
     'type': u'regular'},
    {'affiliations': [u'Rensselaer Polytechnic Institute, Troy, N.Y.'],
     'emails': [],
     'name': {'native': None,
      'normalized': u'Motamedi, M',
      'western': u'Motamedi, M. E.'},
     'number': u'3',
     'orcid': None,
     'type': u'regular'},
    {'affiliations': [u'LNR Communications, Inc., Hauppauge, N.Y.'],
     'emails': [],
     'name': {'native': None,
      'normalized': u'Tam, K',
      'western': u'Tam, K. -Y.'},
     'number': u'4',
     'orcid': None,
     'type': u'regular'},
    {'affiliations': [u'LNR Communications, Inc., Hauppauge, N.Y.'],
     'emails': [],
     'name': {'native': None,
      'normalized': u'Sheu, S',
      'western': u'Sheu, S. -P.'},
     'number': u'5',
     'orcid': None,
     'type': u'regular'}],
   'comment': [],
   'conf_metadata': {'content': None, 'origin': u'STI'},
   'copyright': [],
   'doi': [{'content': u'10.1109/T-ED.1980.19830', 'origin': u'STI'}],
   'isbns': [],
   'issns': [],
   'keywords': [{'channel': u'',
     'normalized': None,
     'origin': u'STI',
     'original': u'Heterojunction Devices',
     'type': u'NASA/STI'},
    {'channel': u'',
     'normalized': u'astronomy infrared',
     'origin': u'STI',
     'original': u'Infrared Spectroscopy',
     'type': u'NASA/STI'},
    {'channel': u'',
     'normalized': None,
     'origin': u'STI',
     'original': u'Lead Sulfides',
     'type': u'NASA/STI'},
    {'channel': u'',
     'normalized': u'silicates',
     'origin': u'STI',
     'original': u'Silicon Junctions',
     'type': u'NASA/STI'},
    {'channel': u'',
     'normalized': u'techniques spectroscopic',
     'origin': u'STI',
     'original': u'Spectral Reflectance',
     'type': u'NASA/STI'},
    {'channel': u'',
     'normalized': None,
     'origin': u'STI',
     'original': u'Volt-Ampere Characteristics',
     'type': u'NASA/STI'},
    {'channel': u'',
     'normalized': u'astronomy infrared',
     'origin': u'STI',
     'original': u'Infrared Detectors',
     'type': u'NASA/STI'},
    {'channel': u'',
     'normalized': u'astronomy infrared',
     'origin': u'STI',
     'original': u'Infrared Reflection',
     'type': u'NASA/STI'},
    {'channel': u'',
     'normalized': u'astronomy visual',
     'origin': u'STI',
     'original': u'Optical Properties',
     'type': u'NASA/STI'},
    {'channel': u'',
     'normalized': u'photoabsorption',
     'origin': u'STI',
     'original': u'Photoabsorption',
     'type': u'NASA/STI'},
    {'channel': u'',
     'normalized': None,
     'origin': u'STI',
     'original': u'Thin Films',
     'type': u'NASA/STI'},
    {'channel': u'',
     'normalized': None,
     'origin': u'STI',
     'original': u'Transmittance',
     'type': u'NASA/STI'},
    {'channel': u'',
     'normalized': None,
     'origin': u'STI',
     'original': u'Solid-State Physics',
     'type': u'STI category'}],
   'language': '',
   'publication': {'altbibcode': u'1980ITED...27..126S',
    'dates': [{'content': u'1980-01-00', 'type': u'date-published'},
     {'content': u'1980', 'type': 'publication_year'}],
    'electronic_id': None,
    'issue': None,
    'name': {'canonical': u'IEEE Transactions on Electron Devices',
     'raw': u'IEEE Transactions on Electron Devices, vol. ED-27, Jan. 1980, p. 126-133.'},
    'origin': u'STI',
    'page': u'126',
    'page_count': [u'8', u'8'],
    'page_last': u'133',
    'page_range': [u'126-133', u'126-133'],
    'volume': [u'27', u'27']},
   'pubnote': [],
   'tempdata': {'alternate_journal': False,
    'modtime': u'2017-07-27T21:43:27Z',
    'origin': u'STI',
    'primary': True,
    'type': u'general'},
   'titles': [{'lang': u'en',
     'text': u'The optical and detector properties of the PbS-Si heterojunction'}]},
  {'abstracts': [],
   'arxivcategories': [],
   'authors': [{'affiliations': [],
     'emails': [],
     'name': {'native': None,
      'normalized': u'Steckl, A',
      'western': u'Steckl, A. J.'},
     'number': u'1',
     'orcid': None,
     'type': u'regular'},
    {'affiliations': [],
     'emails': [],
     'name': {'native': None,
      'normalized': u'Elabd, H',
      'western': u'Elabd, H.'},
     'number': u'2',
     'orcid': None,
     'type': u'regular'},
    {'affiliations': [],
     'emails': [],
     'name': {'native': None,
      'normalized': u'Ka-Yee Tam,',
      'western': u'Ka-Yee Tam'},
     'number': u'3',
     'orcid': None,
     'type': u'regular'},
    {'affiliations': [],
     'emails': [],
     'name': {'native': None,
      'normalized': u'Shey-Ping Sheu,',
      'western': u'Shey-Ping Sheu'},
     'number': u'4',
     'orcid': None,
     'type': u'regular'},
    {'affiliations': [],
     'emails': [],
     'name': {'native': None,
      'normalized': u'Motamedi, M',
      'western': u'Motamedi, M. E.'},
     'number': u'5',
     'orcid': None,
     'type': u'regular'}],
   'comment': [],
   'conf_metadata': {'content': None, 'origin': u'CROSSREF'},
   'copyright': [],
   'doi': [{'content': u'10.1109/T-ED.1980.19830', 'origin': u'CROSSREF'}],
   'isbns': [],
   'issns': [],
   'keywords': [],
   'language': '',
   'publication': {'altbibcode': u'1980ITED...27..126S',
    'dates': [{'content': u'1980-01-00', 'type': u'date-published'},
     {'content': u'1980', 'type': 'publication_year'}],
    'electronic_id': None,
    'issue': u'1',
    'name': {'canonical': u'IEEE Transactions on Electron Devices',
     'raw': u'IEEE Transactions on Electron Devices, vol. 27, issue 1, pp. 126-133'},
    'origin': u'CROSSREF',
    'page': u'126',
    'page_count': [u'8', u'8'],
    'page_last': u'133',
    'page_range': [u'126-133', u'126-133'],
    'volume': [u'27', u'27']},
   'pubnote': [],
   'tempdata': {'alternate_journal': False,
    'modtime': u'2017-03-23T20:50:42Z',
    'origin': u'CROSSREF',
    'primary': False,
    'type': u'general'},
   'titles': [{'lang': u'en',
     'text': u'The optical and detector properties of the PbS-Si heterojunction'}]},
  {'ads_openaccess': False,
   'associates': [],
   'bibgroups': [],
   'data_sources': [],
   'databases': [{'content': u'PHY', 'origin': u'ADS metadata'}],
   'doctype': {'content': u'article', 'origin': u'ADS metadata'},
   'eprint_openaccess': False,
   'ocrabstract': False,
   'openaccess': False,
   'private': False,
   'pub_openaccess': False,
   'refereed': True,
   'tempdata': {'alternate_journal': False,
    'modtime': None,
    'origin': u'ADS metadata',
    'primary': False,
    'type': u'properties'},
   'vizier_tables': []},
  {'alternates': [],
   'links': [{'access': None,
     'count': None,
     'origin': None,
     'title': None,
     'type': u'electr',
     'url': u'http://dx.doi.org/10.1109%2FT-ED.1980.19830'}],
   'preprints': [],
   'tempdata': {'alternate_journal': False,
    'modtime': None,
    'origin': u'ADS metadata',
    'primary': False,
    'type': u'relations'}}],
 'modtime': '2017-10-19T00:02:27.042242Z',
 'text': {'acknowledgement': []}}

and new pipeline produces:

{
  "responseHeader":{
    "status":0,
    "QTime":2,
    "params":{
      "q":"bibcode:1980ITED...27..126S",
      "indent":"on",
      "wt":"json"}},
  "response":{"numFound":1,"start":0,"docs":[
      {
        "doctype_facet_hier":["0/Article",
          "1/Article/Journal Article"],
        "update_timestamp":"2017-09-21T00:56:03.764Z",
        "first_author":"Steckl, A. J.",
        "abstract":"The optical and detector properties of PbS-Si heterojunctions (HJ) are studied. The absorption of PbS films and PbS-Si HJ's have been measured by IR spectroscopy. The photosignal and noise measurements of PbS-Si HJ's are outlined. HJ detectivity and its spectral response are emphasized.",
        "keyword_schema":["NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "STI category"],
        "links_data":["{\"access\": \"\", \"instances\": \"\", \"title\": \"\", \"type\": \"electr\", \"url\": \"http://dx.doi.org/10.1109%2FT-ED.1980.19830\"}"],
        "citation_count":6,
        "date":"1980-01-01T00:00:00Z",
        "keyword_norm":["-",
          "astronomy infrared",
          "-",
          "silicates",
          "techniques spectroscopic",
          "-",
          "astronomy infrared",
          "astronomy infrared",
          "astronomy visual",
          "photoabsorption",
          "-",
          "-",
          "-"],
        "year":"1980",
        "property":["REFEREED",
          "ARTICLE"],
        "id":"3622553",
        "recid":3622553,
        "page":["126"],
        "bibcode":"1980ITED...27..126S",
        "identifier":["1980ITED...27..126S",
          "10.1109/T-ED.1980.19830",
          "10.1109/T-ED.1980.19830"],
        "pubdate":"1980-01-00",
        "author":["Steckl, A. J.",
          "Elabd, H.",
          "Motamedi, M. E.",
          "Tam, K. -Y.",
          "Sheu, S. -P."],
        "aff":["Rensselaer Polytechnic Institute, Troy, N.Y.",
          "Rensselaer Polytechnic Institute, Troy, N.Y.",
          "Rensselaer Polytechnic Institute, Troy, N.Y.",
          "LNR Communications, Inc., Hauppauge, N.Y.",
          "LNR Communications, Inc., Hauppauge, N.Y."],
        "orcid_pub":["-",
          "-",
          "-",
          "-",
          "-"],
        "metrics_mtime":"2017-09-20T03:46:19.805Z",
        "keyword_facet":["astronomy infrared",
          "silicates",
          "techniques spectroscopic",
          "astronomy infrared",
          "astronomy infrared",
          "astronomy visual",
          "photoabsorption"],
        "email":["-",
          "-",
          "-",
          "-",
          "-"],
        "citation":["1980TSF....74...23R",
          "1988PQE....12...87R",
          "1997InPhT..38....9Y",
          "2000Semic..34.1295A",
          "2011TSF...519.2287M",
          "2016SuMi...89...43H"],
        "metadata_mtime":"2017-09-20T09:43:24.187Z",
        "volume":"27",
        "doi":["10.1109/T-ED.1980.19830"],
        "pub":"IEEE Transactions on Electron Devices",
        "first_author_norm":"Steckl, A",
        "keyword":["Heterojunction Devices",
          "Infrared Spectroscopy",
          "Lead Sulfides",
          "Silicon Junctions",
          "Spectral Reflectance",
          "Volt-Ampere Characteristics",
          "Infrared Detectors",
          "Infrared Reflection",
          "Optical Properties",
          "Photoabsorption",
          "Thin Films",
          "Transmittance",
          "Solid-State Physics"],
        "database":["physics"],
        "doctype":"article",
        "pub_raw":"IEEE Transactions on Electron Devices, vol. ED-27, Jan. 1980, p. 126-133.",
        "cite_read_boost":0.19,
        "title":["The optical and detector properties of the PbS-Si heterojunction"],
        "nonbib_mtime":"2017-09-21T00:56:03.764Z",
        "author_norm":["Steckl, A",
          "Elabd, H",
          "Motamedi, M",
          "Tam, K",
          "Sheu, S"],
        "_version_":1579845489159831552,
        "indexstamp":"2017-09-29T04:07:41.380Z"}]
  }}

the old produces

{
  "responseHeader":{
    "status":0,
    "QTime":1,
    "params":{
      "q":"bibcode:1980ITED...27..126S",
      "indent":"on",
      "wt":"json"}},
  "response":{"numFound":1,"start":0,"docs":[
      {
        "read_count":0,
        "identifier":["10.1109/T-ED.1980.19830",
          "10.1109/T-ED.1980.19830",
          "1980ITED...27..126S"],
        "pubdate":"1980-01-00",
        "first_author":"Steckl, A. J.",
        "abstract":"The optical and detector properties of PbS-Si heterojunctions (HJ) are studied. The absorption of PbS films and PbS-Si HJ's have been measured by IR spectroscopy. The photosignal and noise measurements of PbS-Si HJ's are outlined. HJ detectivity and its spectral response are emphasized.",
        "citation":["1980TSF....74...23R",
          "1988PQE....12...87R",
          "1997InPhT..38....9Y",
          "2000Semic..34.1295A",
          "2011TSF...519.2287M",
          "2016SuMi...89...43H"],
        "links_data":["{\"title\":\"\", \"type\":\"electr\", \"instances\":\"\", \"access\":\"\"}"],
        "pub":"IEEE Transactions on Electron Devices",
        "citation_count":6,
        "volume":"27",
        "date":"1980-01-01T00:00:00Z",
        "keyword_norm":["-",
          "astronomy infrared",
          "-",
          "silicates",
          "techniques spectroscopic",
          "-",
          "astronomy infrared",
          "astronomy infrared",
          "astronomy visual",
          "photoabsorption",
          "-",
          "-",
          "-"],
        "doi":["10.1109/T-ED.1980.19830"],
        "author_norm":["Steckl, A",
          "Elabd, H",
          "Ka-Yee Tam,",
          "Shey-Ping Sheu,",
          "Motamedi, M"],
        "year":"1980",
        "first_author_norm":"Steckl, A",
        "property":["REFEREED",
          "ARTICLE"],
        "id":"3554174",
        "recid":3554174,
        "page":["126"],
        "bibcode":"1980ITED...27..126S",
        "classic_factor":4225,
        "keyword":["Heterojunction Devices",
          "Infrared Spectroscopy",
          "Lead Sulfides",
          "Silicon Junctions",
          "Spectral Reflectance",
          "Volt-Ampere Characteristics",
          "Infrared Detectors",
          "Infrared Reflection",
          "Optical Properties",
          "Photoabsorption",
          "Thin Films",
          "Transmittance",
          "Solid-State Physics"],
        "author":["Steckl, A. J.",
          "Elabd, H.",
          "Ka-Yee Tam",
          "Shey-Ping Sheu",
          "Motamedi, M. E."],
        "aff":["Rensselaer Polytechnic Institute, Troy, N.Y.",
          "Rensselaer Polytechnic Institute, Troy, N.Y.",
          "-",
          "-",
          "Rensselaer Polytechnic Institute, Troy, N.Y."],
        "database":["physics"],
        "orcid_pub":["-",
          "-",
          "-",
          "-",
          "-"],
        "doctype":"article",
        "pub_raw":"IEEE Transactions on Electron Devices, vol. ED-27, Jan. 1980, p. 126-133.",
        "cite_read_boost":0.19,
        "title":["The optical and detector properties of the PbS-Si heterojunction"],
        "keyword_schema":["NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "NASA/STI",
          "STI category"],
        "keyword_facet":["astronomy infrared",
          "silicates",
          "techniques spectroscopic",
          "astronomy infrared",
          "astronomy infrared",
          "astronomy visual",
          "photoabsorption"],
        "email":["-",
          "-",
          "-",
          "-",
          "-"],
        "_version_":1581272009309945860,
        "indexstamp":"2017-10-14T22:01:42.531Z",
        "update_timestamp":"2017-10-14T22:01:42.531Z"}]
  }}