Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
DUMMY_FOLDER_LABEL |
"none" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final int |
Article |
3 |
public static final int |
Book |
0 |
public static final int |
Digital_support |
2 |
public static final int |
InBook |
5 |
public static final int |
InCollection |
7 |
public static final int |
InProceedings |
6 |
public static final int |
Manual |
8 |
public static final int |
MasterThesis |
10 |
public static final int |
Periodical |
1 |
public static final int |
PhdThesis |
11 |
public static final int |
Proceedings |
13 |
public static final int |
Serie |
14 |
public static final int |
TechReport |
9 |
public static final int |
Unknown |
4 |
public static final int |
Unpublished |
12 |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final double |
GROBID_TOKEN_DEFAULT_DOUBLE |
-1.0 |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final int |
MAX_FIG_BOX_DISTANCE |
70 |
protected static final int |
nbBins |
12 |
public static final long |
serialVersionUID |
1L |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final int |
PDFTOXML_FILES_AMOUNT_LIMIT |
5000 |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
TEI_NS |
"http://www.tei-c.org/ns/1.0" |
public static final java.lang.String |
XML_NS |
"http://www.w3.org/XML/1998/namespace" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
ACKNOWLEDGEMENT_LABEL |
"<acknowledgement>" |
public static final java.lang.String |
ANNEX_LABEL |
"<annex>" |
public static final java.lang.String |
BODY_LABEL |
"<body>" |
public static final java.lang.String |
COVER_LABEL |
"<cover>" |
public static final java.lang.String |
FOOTNOTE_LABEL |
"<footnote>" |
public static final java.lang.String |
HEADER_LABEL |
"<header>" |
public static final java.lang.String |
HEADNOTE_LABEL |
"<headnote>" |
public static final java.lang.String |
MARGINNOTE_LABEL |
"<marginnote>" |
public static final java.lang.String |
PAGE_NUMBER_LABEL |
"<page>" |
public static final java.lang.String |
REFERENCES_LABEL |
"<references>" |
public static final java.lang.String |
TOC_LABEL |
"<toc>" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final long |
serialVersionUID |
1L |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
ABSTRACT_LABEL |
"<abstract>" |
public static final java.lang.String |
ADDRESS_LABEL |
"<address>" |
public static final java.lang.String |
ADVERTISEMENT_LABEL |
"<advertisement>" |
public static final java.lang.String |
AFFILIATION_LABEL |
"<affiliation>" |
public static final java.lang.String |
ANNEX_LABEL |
"<annex>" |
public static final java.lang.String |
AUTHOR_LABEL |
"<author>" |
public static final java.lang.String |
BACK_LABEL |
"<back>" |
public static final java.lang.String |
BIOGRAPHY_LABEL |
"<biography>" |
public static final java.lang.String |
BOOKTITLE_LABEL |
"<booktitle>" |
public static final java.lang.String |
CITATION_MARKER_LABEL |
"<citation_marker>" |
public static final java.lang.String |
COLLABORATION_LABEL |
"<collaboration>" |
public static final java.lang.String |
CONTENT_LABEL |
"<content>" |
public static final java.lang.String |
COPYRIGHT_LABEL |
"<copyright>" |
public static final java.lang.String |
COVER_LABEL |
"<cover>" |
public static final java.lang.String |
DATE_DAY_LABEL |
"<day>" |
public static final java.lang.String |
DATE_LABEL |
"<date>" |
public static final java.lang.String |
DATE_MONTH_LABEL |
"<month>" |
public static final java.lang.String |
DATE_YEAR_LABEL |
"<year>" |
public static final java.lang.String |
DATESUB_LABEL |
"<date-submission>" |
public static final java.lang.String |
DEDICATION_LABEL |
"<dedication>" |
public static final java.lang.String |
DEGREE_LABEL |
"<degree>" |
public static final java.lang.String |
DESCRIPTION_LABEL |
"<figDesc>" |
public static final java.lang.String |
EDITOR_LABEL |
"<editor>" |
public static final java.lang.String |
EMAIL_LABEL |
"<email>" |
public static final java.lang.String |
ENAMEX_START_ENTITY_LABEL_PREFIX |
"E-" |
public static final java.lang.String |
ENTITLE_LABEL |
"<entitle>" |
public static final java.lang.String |
EQUATION_ID_LABEL |
"<equation_label>" |
public static final java.lang.String |
EQUATION_LAB |
"<equation>" |
public static final java.lang.String |
EQUATION_MARKER_LABEL |
"<equation_marker>" |
public static final java.lang.String |
FIGURE_LABEL |
"<figure>" |
public static final java.lang.String |
FIGURE_MARKER_LABEL |
"<figure_marker>" |
public static final java.lang.String |
FORENAME_LABEL |
"<forename>" |
public static final java.lang.String |
GLOSSARY_LABEL |
"<glossary>" |
public static final java.lang.String |
GRANT_LABEL |
"<grant>" |
public static final java.lang.String |
GROBID_INSIDE_ENTITY_LABEL_PREFIX |
"" |
public static final java.lang.String |
GROBID_START_ENTITY_LABEL_PREFIX |
"I-" |
public static final java.lang.String |
HEADER_LABEL |
"<figure_head>" |
public static final java.lang.String |
INDEX_LABEL |
"<index>" |
public static final java.lang.String |
INSTITUTION_LABEL |
"<institution>" |
public static final java.lang.String |
INTRO_LABEL |
"<intro>" |
public static final java.lang.String |
IOB_INSIDE_LABEL_PREFIX |
"I-" |
public static final java.lang.String |
IOB_OTHER_LABEL |
"O" |
public static final java.lang.String |
IOB_START_ENTITY_LABEL_PREFIX |
"B-" |
public static final java.lang.String |
ISSUE_LABEL |
"<issue>" |
public static final java.lang.String |
ITEM_LABEL |
"<item>" |
public static final java.lang.String |
JOURNAL_LABEL |
"<journal>" |
public static final java.lang.String |
KEYWORD_LABEL |
"<keyword>" |
public static final java.lang.String |
LABEL_LABEL |
"<label>" |
public static final java.lang.String |
LOCATION_LABEL |
"<location>" |
public static final java.lang.String |
MARKER_LABEL |
"<marker>" |
public static final java.lang.String |
MIDDLENAME_LABEL |
"<middlename>" |
public static final java.lang.String |
NOTE_LABEL |
"<note>" |
public static final java.lang.String |
OTHER_LABEL |
"<other>" |
public static final java.lang.String |
PAGE_LABEL |
"<page>" |
public static final java.lang.String |
PAGES_LABEL |
"<pages>" |
public static final java.lang.String |
PARAGRAPH_LABEL |
"<paragraph>" |
public static final java.lang.String |
PHONE_LABEL |
"<phone>" |
public static final java.lang.String |
PREFACE_LABEL |
"<preface>" |
public static final java.lang.String |
PUBLISHER_LABEL |
"<publisher>" |
public static final java.lang.String |
PUBNUM_LABEL |
"<pubnum>" |
public static final java.lang.String |
REFERENCE_LABEL |
"<reference>" |
public static final java.lang.String |
SECTION_LABEL |
"<section>" |
public static final java.lang.String |
SUBMISSION_LABEL |
"<submission>" |
public static final java.lang.String |
SUFFIX_LABEL |
"<suffix>" |
public static final java.lang.String |
SUMMARY_LABEL |
"<summary>" |
public static final java.lang.String |
SURNAME_LABEL |
"<surname>" |
public static final java.lang.String |
TABLE_LABEL |
"<table>" |
public static final java.lang.String |
TABLE_MARKER_LABEL |
"<table_marker>" |
public static final java.lang.String |
TECH_LABEL |
"<tech>" |
public static final java.lang.String |
TITLE_LABEL |
"<title>" |
public static final java.lang.String |
TOC_LABEL |
"<toc>" |
public static final java.lang.String |
TOF_LABEL |
"<tof>" |
public static final java.lang.String |
UNIT_LABEL |
"<unit>" |
public static final java.lang.String |
VOLUME_LABEL |
"<volume>" |
public static final java.lang.String |
WEB_LABEL |
"<web>" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
DUMMY_LABEL |
"<dummy>" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
START_ENTITY_LABEL_PREFIX |
"I-" |
public static final java.lang.String |
START_ENTITY_LABEL_PREFIX_ALTERNATIVE |
"B-" |
public static final java.lang.String |
START_ENTITY_LABEL_PREFIX_ALTERNATIVE_2 |
"E-" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
DE |
"de" |
public static final java.lang.String |
EN |
"en" |
public static final java.lang.String |
ES |
"es" |
public static final java.lang.String |
FR |
"fr" |
public static final java.lang.String |
IT |
"it" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final int |
MINIMUM_VECTOR_BOX_AREA |
3000 |
public static final int |
VEC_GRAPHICS_FILE_SIZE_LIMIT |
10485760 |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
CRFPP_NATIVE_LIB_NAME |
"libcrfpp" |
public static final java.lang.String |
DELFT_NATIVE_LIB_NAME |
"jep" |
public static final java.lang.String |
DELFT_NATIVE_LIB_NAME_LINUX |
"libjep" |
public static final java.lang.String |
WAPITI_NATIVE_LIB_NAME |
"libwapiti" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
xsltPath |
"/xslt/grobid-jats.xsl" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final int |
CUT_DEFAULT_LENGTH |
50 |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
FILE_ENDING_TEI_FULLTEXT |
".fulltext.tei.xml" |
public static final java.lang.String |
FILE_ENDING_TEI_HEADER |
".header.tei.xml" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
PROP_3RD_PARTY_PDFTOXML |
"grobid.3rdparty.pdf2xml.path" |
public static final java.lang.String |
PROP_3RD_PARTY_PDFTOXML_MEMORY_LIMIT |
"grobid.3rdparty.pdf2xml.memory.limit.mb" |
public static final java.lang.String |
PROP_3RD_PARTY_PDFTOXML_TIMEOUT_SEC |
"grobid.3rdparty.pdf2xml.memory.timeout.sec" |
public static final java.lang.String |
PROP_CONSOLIDATION_SERVICE |
"grobid.consolidation.service" |
public static final java.lang.String |
PROP_CROSSREF_HOST |
"grobid.crossref_host" |
public static final java.lang.String |
PROP_CROSSREF_ID |
"grobid.crossref_id" |
public static final java.lang.String |
PROP_CROSSREF_MAILTO |
"org.grobid.crossref.mailto" |
public static final java.lang.String |
PROP_CROSSREF_PORT |
"grobid.crossref_port" |
public static final java.lang.String |
PROP_CROSSREF_PW |
"grobid.crossref_pw" |
public static final java.lang.String |
PROP_CROSSREF_TOKEN |
"org.grobid.crossref.token" |
public static final java.lang.String |
PROP_GLUTTON_HOST |
"org.grobid.glutton.host" |
public static final java.lang.String |
PROP_GLUTTON_PORT |
"org.grobid.glutton.port" |
public static final java.lang.String |
PROP_GROBID_CRF_ENGINE |
"grobid.crf.engine" |
public static final java.lang.String |
PROP_GROBID_DELFT_ELMO |
"grobid.delft.useELMo" |
public static final java.lang.String |
PROP_GROBID_DELFT_PATH |
"grobid.delft.install" |
public static final java.lang.String |
PROP_GROBID_DELFT_REDIRECT_OUTPUT |
"grobid.delft.redirect_output" |
public static final java.lang.String |
PROP_GROBID_HOME |
"org.grobid.home" |
public static final java.lang.String |
PROP_GROBID_IS_CONTEXT_SERVER |
"grobid.is.context.server" |
public static final java.lang.String |
PROP_GROBID_MAX_CONNECTIONS |
"org.grobid.max.connections" |
public static final java.lang.String |
PROP_GROBID_POOL_MAX_WAIT |
"org.grobid.pool.max.wait" |
public static final java.lang.String |
PROP_GROBID_PROPERTY |
"org.grobid.property" |
public static final java.lang.String |
PROP_GROBID_SERVICE_ADMIN_PW |
"org.grobid.service.admin.pw" |
public static final java.lang.String |
PROP_GROBID_SERVICE_IS_PARALLEL_EXEC |
"org.grobid.service.is.parallel.execution" |
public static final java.lang.String |
PROP_GROBID_VERSION |
"org.grobid.version" |
public static final java.lang.String |
PROP_HEADER_USE_HEURISTICS |
"grobid.header.use_heuristics" |
public static final java.lang.String |
PROP_LANG_DETECTOR_FACTORY |
"grobid.language_detector_factory" |
public static final java.lang.String |
PROP_NATIVE_LIB_PATH |
"grobid.nativelibrary.path" |
public static final java.lang.String |
PROP_NB_THREADS |
"grobid.nb_threads" |
public static final java.lang.String |
PROP_PDF_BLOCKS_MAX |
"grobid.pdf.blocks.max" |
public static final java.lang.String |
PROP_PDF_TOKENS_MAX |
"grobid.pdf.tokens.max" |
public static final java.lang.String |
PROP_PROXY_HOST |
"grobid.proxy_host" |
public static final java.lang.String |
PROP_PROXY_PORT |
"grobid.proxy_port" |
public static final java.lang.String |
PROP_RESOURCE_INHOME |
"grobid.resources.inHome" |
public static final java.lang.String |
PROP_TMP_PATH |
"grobid.temp.path" |
public static final java.lang.String |
PROP_USE_LANG_ID |
"grobid.use_language_id" |
public static final java.lang.String |
PYTHON_VIRTUALENV_DIRECTORY |
"grobid.delft.python.virtualEnv" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final int |
MIN_LENGTH |
10 |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
AND |
"&" |
public static final java.lang.String |
COLON |
":" |
public static final java.lang.String |
COMMA |
"," |
public static final java.lang.String |
DOUBLE_QUOTE |
"\"" |
public static final java.lang.String |
END_BRACKET |
")" |
public static final java.lang.String |
ESC_AND |
"&" |
public static final java.lang.String |
ESC_DOUBLE_QUOTE |
""" |
public static final java.lang.String |
ESC_GREATER_THAN |
">" |
public static final java.lang.String |
ESC_LESS_THAN |
"<" |
public static final java.lang.String |
fullPunctuations |
"(\uff08[ \u2022*,:;?.!/)\uff09-\u2212\u2013\u2010\u00ab\u00bb\u201e\"\u201c\u201d\u2018\u2019\'`$]*\u2666\u2665\u2663\u2660\u00a0" |
public static final java.lang.String |
GREATER_THAN |
">" |
public static final java.lang.String |
LESS_THAN |
"<" |
public static final java.lang.String |
NEW_LINE |
"\n" |
public static final java.lang.String |
OR |
"|" |
public static final java.lang.String |
punctuations |
" \u2022*,:;?.!)-\u2212\u2013\"\u201c\u201d\u2018\u2019\'`$]*\u2666\u2665\u2663\u2660\u00a0" |
public static final java.lang.String |
QUOTE |
"\'" |
public static final java.lang.String |
restrictedPunctuations |
",:;?.!/-\u2013\u00ab\u00bb\u201e\"\u201c\u201d\u2018\u2019\'`*\u2666\u2665\u2663\u2660" |
public static final java.lang.String |
SHARP |
"#" |
public static final java.lang.String |
SLASH |
"/" |
public static final java.lang.String |
SPACE |
" " |
public static final java.lang.String |
START_BRACKET |
"(" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
START |
"START" |
public static final java.lang.String |
STOP |
"STOP" |
Modifier and Type | Constant Field | Value |
---|---|---|
protected static final java.lang.String |
BASE_URL |
"https://api.crossref.org" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final java.lang.String |
INDEXED_LUCENE_FIELD_NAME |
"indexedField" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final int |
MAX_RANGE |
20 |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final boolean |
VISUALIZE_VECTOR_BOXES |
true |