articles.py 11.3 KB
Newer Older
1 2 3 4 5 6 7
# -*- coding: utf-8 -*-
""" harvest_tools.articles

"""
import traceback


8
from automaton import Automaton
9 10
from base import (family_name_fr,
                  format_author_fr,
11
                  learn_my_authors,
12 13 14 15
                  MSG_CRASH,
                  MSG_FIX_ORIGIN,
                  MSG_IN_DB,
                  MSG_LOAD)
16 17 18 19
from invenio_tools import CheckException
from plugin_dbui import get_id, UNDEF_ID


20 21
MSG_NO_EDITOR = "Reject article is not published"
MSG_TRANSFORM_PREPRINT = "Transform the preprint into an article"
22 23


24
class Articles(Automaton):
25
    """Automaton for articles.
26 27 28 29

    """
    def __init__(self, *args, **kwargs):

30
        Automaton.__init__(self, *args, **kwargs)
31 32 33 34

        # the preprint categories
        self.id_preprint = get_id(self.db.categories, code="PRE")

35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58
    def check_record(self, record):
        """Check the content of the article in order to fix non conformities.

        @type record: L{Record}
        @param record:

        @rtype: bool
        @return: C{False} when a non conformity is found and can not be
        corrected.

        """
        if not Automaton.check_record(self, record):
            return False

        if self.dbg:
            print "select article record"

        try:
            self.check.clean_erratum(record)

            if not record.is_published():
                self.logs[-1].reject(MSG_NO_EDITOR, record.year())
                return False

59
            self.check.paper_reference(record)
60 61 62 63
            self.check.submitted(record)
            self.check.year(record)

            self.check.format_editor(record)
64 65 66 67
            self.check.format_authors(record, format_author_fr)

            self.check.get_my_authors(record, family_name_fr)
            self.check.fix_oai(record)
68 69 70 71 72 73 74 75 76 77 78 79

        except CheckException as e:
            self.logs[-1].reject(e, record.year())
            return False

        except Exception as e:
            self.logs[-1].reject(MSG_CRASH % e, record.year(), translate=False)
            print traceback.format_exc()
            return False

        return True

80 81 82 83 84 85 86 87 88
    def get_record_by_origin(self,
                             id_publisher=None,
                             my_authors=None,
                             oai_url=None,
                             pages=None,
                             publication_url=None,
                             title=None,
                             volume=None,
                             year=None):
89
        """Get an existing record using the origin field.
90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136

            - Transform a preprint into article.
            - Actions are logged.

        @keyword id_publisher:
        @keyword oai_url:
        @keyword pages:
        @keyword publication_url:
        @keyword title:
        @keyword volume:
        @keyword year:

        @rtype: tuple
        @return: the tuple (id, status). The id of the record or None.
        The status is equal to one when the existing record was modified
        zero otherwise

        """
        if self.dbg:
            print "check existing article by origin"

        db = self.db

        rec_id = get_id(db.publications, origin=oai_url)
        if not rec_id:
            return (None, 0)

        # not a preprint ?
        if db.publications[rec_id].id_categories != self.id_preprint:
            self.logs[-1].idle(MSG_IN_DB, year)
            return (rec_id, 0)

        # transform a preprint into an article
        self.logs[-1].modify(MSG_TRANSFORM_PREPRINT, year)
        if not self.dry_run:
            db.publications[rec_id] = dict(authors_institute=my_authors,
                                           id_categories=self.id_category,
                                           id_publishers=id_publisher,
                                           id_status=UNDEF_ID,
                                           pages=pages,
                                           publication_url=publication_url,
                                           title=title,
                                           volume=volume,
                                           year=year)

        return (rec_id, 1)

137 138 139 140 141 142 143 144 145 146
    def get_record_by_fields(self,
                             id_publisher=None,
                             my_authors=None,
                             oai_url=None,
                             pages=None,
                             publication_url=None,
                             preprint_number=None,
                             title=None,
                             volume=None,
                             year=None):
147
        """Get a record matching the fields: id_projects,
148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169
        id_publishers, id_teams, pages, volume and year.

            - Fix the field origin when a match is found.
            - Transform a preprint into article.
            - Actions are logged.

        @keyword id_publisher:
        @keyword oai_url:
        @keyword pages:
        @keyword publication_url:
        @keyword preprint_number:
        @keyword title:
        @keyword volume:
        @keyword year:

        @rtype: tuple
        @return: the tuple (id, status). The id of the record or None.
        The status is equal to one when the existing record was modified
        zero otherwise

        """
        if self.dbg:
170
            print "get existing article by fields"
171 172 173 174 175 176 177 178 179 180 181 182

        db = self.db

        # check against published articles
        rec_id = get_id(db.publications,
                        id_projects=self.id_project,
                        id_publishers=id_publisher,
                        id_teams=self.id_team,
                        pages=pages,
                        volume=volume,
                        year=year)

183
        # fix origin field
184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223
        if rec_id and not db.publications[rec_id].origin:
            if not self.dry_run:
                db.publications[rec_id] = dict(origin=oai_url)

            self.logs[-1].modify(MSG_FIX_ORIGIN, year)
            return (rec_id, 1)

        if rec_id:
            self.logs[-1].idle(MSG_IN_DB, year)
            return (rec_id, 0)

        # check against published preprint
        # a preprint can be identified by its category which is PRE (15)
        rec_id = get_id(db.publications,
                        id_categories=self.id_preprint,
                        id_projects=self.id_project,
                        id_teams=self.id_team,
                        preprint=preprint_number)

        if not rec_id:
            return (None, 0)

        # transform an existing preprint into article
        # institute authors can be missing in the preprint
        # change also the status
        self.logs[-1].modify(MSG_TRANSFORM_PREPRINT, year)

        if not self.dry_run:
            db.publications[rec_id] = dict(authors_institute=my_authors,
                                           id_categories=self.id_category,
                                           id_publishers=id_publisher,
                                           id_status=UNDEF_ID,
                                           pages=pages,
                                           publication_url=publication_url,
                                           title=title,
                                           volume=volume,
                                           year=year)

        return (rec_id, 1)

224 225
    def insert_record(self, record):
        """Insert an article in the database.
226 227 228 229 230 231 232 233 234 235 236 237 238 239 240
        The method assume that erratum are removed.

        @type record: L{Record}
        @param record:

        @rtype: int
        @return: one when the record is inserted / updated in the database
        zero otherwise.

        """
        db = self.db

        # alias
        editor = record.paper_editor()
        first_author = record.first_author()
241
        my_authors = record.my_authors
242 243 244 245 246 247 248 249 250
        oai_url = record.oai_url()
        pages = record.paper_pages()
        preprint_number = record.preprint_number()
        publication_url = record.paper_url()
        submitted = record.submitted()[0]
        title = record.title()
        volume = record.paper_volume()
        year = record.paper_year()

251 252
        # get the publisher / collaboration identifier
        id_publisher = self.get_create_publisher(editor)
253
        id_collaboration = self.get_create_collaboration(record.collaboration())
254

255 256
        # get already published articles or preprint
        # A preprint is transform into an article.
257 258 259
        #
        # NOTE: The check is performed by origin then by fields.
        # The latter is useful to cover the case where the record
260
        # is entered by hand or by another harvester.
261
        #
262 263 264 265 266 267 268 269
        rec_id, status = self.get_record_by_origin(id_publisher=id_publisher,
                                                   my_authors=my_authors,
                                                   oai_url=oai_url,
                                                   pages=pages,
                                                   publication_url=publication_url,
                                                   title=title,
                                                   volume=volume,
                                                   year=year)
270 271 272
        if rec_id:
            return status

273 274 275 276 277 278 279 280 281
        rec_id, status = self.get_record_by_fields(id_publisher=id_publisher,
                                                   my_authors=my_authors,
                                                   oai_url=oai_url,
                                                   pages=pages,
                                                   publication_url=publication_url,
                                                   preprint_number=preprint_number,
                                                   title=title,
                                                   volume=volume,
                                                   year=year)
282 283 284 285 286 287 288
        if rec_id:
            return status

        # eventually insert a new articles in the database
        # try to improve the rescue list for CPPM authors
        if not self.dry_run:

289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321
            ret = self._insert_in_db(log_year=year,
                                     authors=record.authors(),
                                     authors_institute=my_authors,
                                     first_author=first_author,
                                     id_categories=self.id_category,
                                     id_collaborations=id_collaboration,
                                     id_projects=self.id_project,
                                     id_publishers=id_publisher,
                                     id_status=UNDEF_ID,
                                     id_teams=self.id_team,
                                     origin=oai_url,
                                     pages=pages,
                                     preprint=preprint_number,
                                     publication_url=publication_url,
                                     submitted=submitted,
                                     title=title,
                                     volume=volume,
                                     year=year)

            if ret == 1:
                learn_my_authors(db,
                                 authors=record.my_authors,
                                 id_project=self.id_project,
                                 id_team=self.id_team,
                                 year=year)

                self.logs[-1].load(MSG_LOAD, year)

        else:
            ret = 1
            self.logs[-1].load(MSG_LOAD, year)

        return ret