Upload tokenizer

added_tokens.json

@@ -0,0 +1,557 @@
+{
+  "</abbr>": 30905,
+  "</abstract>": 30856,
+  "</accessrestrict>": 30857,
+  "</accruals>": 30858,
+  "</acqinfo>": 30859,
+  "</address>": 30906,
+  "</addressline>": 30907,
+  "</altformavail>": 30860,
+  "</appraisal>": 30861,
+  "</arc>": 30944,
+  "</archdesc>": 30837,
+  "</archdescgrp>": 30838,
+  "</archref>": 30862,
+  "</arrangement>": 30863,
+  "</author>": 30814,
+  "</bibliography>": 30864,
+  "</bibref>": 30865,
+  "</bibseries>": 30908,
+  "</bioghist>": 30866,
+  "</blockquote>": 30909,
+  "</c01>": 30840,
+  "</c02>": 30841,
+  "</c03>": 30842,
+  "</c04>": 30843,
+  "</c05>": 30844,
+  "</c06>": 30845,
+  "</c07>": 30846,
+  "</c08>": 30847,
+  "</c09>": 30848,
+  "</c10>": 30849,
+  "</c11>": 30850,
+  "</c12>": 30851,
+  "</c>": 30839,
+  "</change>": 30815,
+  "</chronitem>": 30910,
+  "</chronlist>": 30911,
+  "</colspec>": 30912,
+  "</container>": 30867,
+  "</controlaccess>": 30852,
+  "</corpname>": 30894,
+  "</creation>": 30816,
+  "</custodhist>": 30868,
+  "</dao>": 30945,
+  "</daodesc>": 30946,
+  "</daogrp>": 30947,
+  "</daoloc>": 30948,
+  "</date>": 30869,
+  "</defitem>": 30913,
+  "</descgrp>": 30914,
+  "</descrules>": 30817,
+  "</did>": 30853,
+  "</dimensions>": 30870,
+  "</div>": 30915,
+  "</dsc>": 30854,
+  "</dscgrp>": 30855,
+  "</ead>": 30818,
+  "</eadgrp>": 30819,
+  "</eadheader>": 30820,
+  "</eadid>": 30821,
+  "</edition>": 30822,
+  "</editionstmt>": 30823,
+  "</emph>": 30916,
+  "</entry>": 30917,
+  "</event>": 30918,
+  "</eventgrp>": 30919,
+  "</expan>": 30920,
+  "</extent>": 30871,
+  "</extptr>": 30949,
+  "</extptrloc>": 30950,
+  "</extref>": 30951,
+  "</extrefloc>": 30952,
+  "</famname>": 30895,
+  "</filedesc>": 30824,
+  "</fileplan>": 30872,
+  "</frontmatter>": 30825,
+  "</function>": 30896,
+  "</genreform>": 30897,
+  "</geogname>": 30898,
+  "</head01>": 30922,
+  "</head02>": 30923,
+  "</head>": 30921,
+  "</imprint>": 30924,
+  "</index>": 30925,
+  "</indexentry>": 30926,
+  "</item>": 30927,
+  "</label>": 30928,
+  "</langmaterial>": 30873,
+  "</language>": 30899,
+  "</langusage>": 30826,
+  "</lb>": 30929,
+  "</legalstatus>": 30874,
+  "</linkgrp>": 30953,
+  "</list>": 30930,
+  "</listhead>": 30931,
+  "</materialspec>": 30875,
+  "</name>": 30900,
+  "</namegrp>": 30932,
+  "</note>": 30933,
+  "</notestmt>": 30827,
+  "</num>": 30934,
+  "</occupation>": 30901,
+  "</odd>": 30876,
+  "</originalsloc>": 30877,
+  "</origination>": 30878,
+  "</otherfindaid>": 30879,
+  "</p>": 30935,
+  "</persname>": 30902,
+  "</physdesc>": 30880,
+  "</physfacet>": 30881,
+  "</physloc>": 30882,
+  "</phystech>": 30883,
+  "</prefercite>": 30884,
+  "</processinfo>": 30885,
+  "</profiledesc>": 30828,
+  "</ptr>": 30954,
+  "</ptrgrp>": 30955,
+  "</ptrloc>": 30956,
+  "</publicationstmt>": 30829,
+  "</publisher>": 30830,
+  "</ref>": 30957,
+  "</refloc>": 30958,
+  "</relatedmaterial>": 30886,
+  "</repository>": 30887,
+  "</resource>": 30959,
+  "</revisiondesc>": 30831,
+  "</row>": 30936,
+  "</runner>": 30937,
+  "</scopecontent>": 30888,
+  "</separatedmaterial>": 30889,
+  "</seriesstmt>": 30832,
+  "</sponsor>": 30833,
+  "</subarea>": 30938,
+  "</subject>": 30903,
+  "</subtitle>": 30834,
+  "</table>": 30939,
+  "</tbody>": 30940,
+  "</tgroup>": 30941,
+  "</thead>": 30942,
+  "</title>": 30904,
+  "</titlepage>": 30943,
+  "</titleproper>": 30835,
+  "</titlestmt>": 30836,
+  "</unitdate>": 30890,
+  "</unitid>": 30891,
+  "</unittitle>": 30892,
+  "</userestrict>": 30893,
+  "<abbr": 30759,
+  "<abbr>": 30613,
+  "<abstract": 30710,
+  "<abstract>": 30564,
+  "<accessrestrict": 30711,
+  "<accessrestrict>": 30565,
+  "<accruals": 30712,
+  "<accruals>": 30566,
+  "<acqinfo": 30713,
+  "<acqinfo>": 30567,
+  "<address": 30760,
+  "<address>": 30614,
+  "<addressline": 30761,
+  "<addressline>": 30615,
+  "<altformavail": 30714,
+  "<altformavail>": 30568,
+  "<appraisal": 30715,
+  "<appraisal>": 30569,
+  "<arc": 30798,
+  "<arc>": 30652,
+  "<archdesc": 30691,
+  "<archdesc>": 30545,
+  "<archdescgrp": 30692,
+  "<archdescgrp>": 30546,
+  "<archref": 30716,
+  "<archref>": 30570,
+  "<arrangement": 30717,
+  "<arrangement>": 30571,
+  "<author": 30668,
+  "<author>": 30522,
+  "<bibliography": 30718,
+  "<bibliography>": 30572,
+  "<bibref": 30719,
+  "<bibref>": 30573,
+  "<bibseries": 30762,
+  "<bibseries>": 30616,
+  "<bioghist": 30720,
+  "<bioghist>": 30574,
+  "<blockquote": 30763,
+  "<blockquote>": 30617,
+  "<c": 30693,
+  "<c01": 30694,
+  "<c01>": 30548,
+  "<c02": 30695,
+  "<c02>": 30549,
+  "<c03": 30696,
+  "<c03>": 30550,
+  "<c04": 30697,
+  "<c04>": 30551,
+  "<c05": 30698,
+  "<c05>": 30552,
+  "<c06": 30699,
+  "<c06>": 30553,
+  "<c07": 30700,
+  "<c07>": 30554,
+  "<c08": 30701,
+  "<c08>": 30555,
+  "<c09": 30702,
+  "<c09>": 30556,
+  "<c10": 30703,
+  "<c10>": 30557,
+  "<c11": 30704,
+  "<c11>": 30558,
+  "<c12": 30705,
+  "<c12>": 30559,
+  "<c>": 30547,
+  "<change": 30669,
+  "<change>": 30523,
+  "<chronitem": 30764,
+  "<chronitem>": 30618,
+  "<chronlist": 30765,
+  "<chronlist>": 30619,
+  "<colspec": 30766,
+  "<colspec>": 30620,
+  "<container": 30721,
+  "<container>": 30575,
+  "<controlaccess": 30706,
+  "<controlaccess>": 30560,
+  "<corpname": 30748,
+  "<corpname>": 30602,
+  "<creation": 30670,
+  "<creation>": 30524,
+  "<custodhist": 30722,
+  "<custodhist>": 30576,
+  "<dao": 30799,
+  "<dao>": 30653,
+  "<daodesc": 30800,
+  "<daodesc>": 30654,
+  "<daogrp": 30801,
+  "<daogrp>": 30655,
+  "<daoloc": 30802,
+  "<daoloc>": 30656,
+  "<date": 30723,
+  "<date>": 30577,
+  "<defitem": 30767,
+  "<defitem>": 30621,
+  "<descgrp": 30768,
+  "<descgrp>": 30622,
+  "<descrules": 30671,
+  "<descrules>": 30525,
+  "<did": 30707,
+  "<did>": 30561,
+  "<dimensions": 30724,
+  "<dimensions>": 30578,
+  "<div": 30769,
+  "<div>": 30623,
+  "<dsc": 30708,
+  "<dsc>": 30562,
+  "<dscgrp": 30709,
+  "<dscgrp>": 30563,
+  "<ead": 30672,
+  "<ead>": 30526,
+  "<eadgrp": 30673,
+  "<eadgrp>": 30527,
+  "<eadheader": 30674,
+  "<eadheader>": 30528,
+  "<eadid": 30675,
+  "<eadid>": 30529,
+  "<edition": 30676,
+  "<edition>": 30530,
+  "<editionstmt": 30677,
+  "<editionstmt>": 30531,
+  "<emph": 30770,
+  "<emph>": 30624,
+  "<entry": 30771,
+  "<entry>": 30625,
+  "<event": 30772,
+  "<event>": 30626,
+  "<eventgrp": 30773,
+  "<eventgrp>": 30627,
+  "<expan": 30774,
+  "<expan>": 30628,
+  "<extent": 30725,
+  "<extent>": 30579,
+  "<extptr": 30803,
+  "<extptr>": 30657,
+  "<extptrloc": 30804,
+  "<extptrloc>": 30658,
+  "<extref": 30805,
+  "<extref>": 30659,
+  "<extrefloc": 30806,
+  "<extrefloc>": 30660,
+  "<famname": 30749,
+  "<famname>": 30603,
+  "<filedesc": 30678,
+  "<filedesc>": 30532,
+  "<fileplan": 30726,
+  "<fileplan>": 30580,
+  "<frontmatter": 30679,
+  "<frontmatter>": 30533,
+  "<function": 30750,
+  "<function>": 30604,
+  "<genreform": 30751,
+  "<genreform>": 30605,
+  "<geogname": 30752,
+  "<geogname>": 30606,
+  "<head": 30775,
+  "<head01": 30776,
+  "<head01>": 30630,
+  "<head02": 30777,
+  "<head02>": 30631,
+  "<head>": 30629,
+  "<imprint": 30778,
+  "<imprint>": 30632,
+  "<index": 30779,
+  "<index>": 30633,
+  "<indexentry": 30780,
+  "<indexentry>": 30634,
+  "<item": 30781,
+  "<item>": 30635,
+  "<label": 30782,
+  "<label>": 30636,
+  "<langmaterial": 30727,
+  "<langmaterial>": 30581,
+  "<language": 30753,
+  "<language>": 30607,
+  "<langusage": 30680,
+  "<langusage>": 30534,
+  "<lb": 30783,
+  "<lb>": 30637,
+  "<legalstatus": 30728,
+  "<legalstatus>": 30582,
+  "<linkgrp": 30807,
+  "<linkgrp>": 30661,
+  "<list": 30784,
+  "<list>": 30638,
+  "<listhead": 30785,
+  "<listhead>": 30639,
+  "<materialspec": 30729,
+  "<materialspec>": 30583,
+  "<name": 30754,
+  "<name>": 30608,
+  "<namegrp": 30786,
+  "<namegrp>": 30640,
+  "<note": 30787,
+  "<note>": 30641,
+  "<notestmt": 30681,
+  "<notestmt>": 30535,
+  "<num": 30788,
+  "<num>": 30642,
+  "<occupation": 30755,
+  "<occupation>": 30609,
+  "<odd": 30730,
+  "<odd>": 30584,
+  "<originalsloc": 30731,
+  "<originalsloc>": 30585,
+  "<origination": 30732,
+  "<origination>": 30586,
+  "<otherfindaid": 30733,
+  "<otherfindaid>": 30587,
+  "<p": 30789,
+  "<p>": 30643,
+  "<persname": 30756,
+  "<persname>": 30610,
+  "<physdesc": 30734,
+  "<physdesc>": 30588,
+  "<physfacet": 30735,
+  "<physfacet>": 30589,
+  "<physloc": 30736,
+  "<physloc>": 30590,
+  "<phystech": 30737,
+  "<phystech>": 30591,
+  "<prefercite": 30738,
+  "<prefercite>": 30592,
+  "<processinfo": 30739,
+  "<processinfo>": 30593,
+  "<profiledesc": 30682,
+  "<profiledesc>": 30536,
+  "<ptr": 30808,
+  "<ptr>": 30662,
+  "<ptrgrp": 30809,
+  "<ptrgrp>": 30663,
+  "<ptrloc": 30810,
+  "<ptrloc>": 30664,
+  "<publicationstmt": 30683,
+  "<publicationstmt>": 30537,
+  "<publisher": 30684,
+  "<publisher>": 30538,
+  "<ref": 30811,
+  "<ref>": 30665,
+  "<refloc": 30812,
+  "<refloc>": 30666,
+  "<relatedmaterial": 30740,
+  "<relatedmaterial>": 30594,
+  "<repository": 30741,
+  "<repository>": 30595,
+  "<resource": 30813,
+  "<resource>": 30667,
+  "<revisiondesc": 30685,
+  "<revisiondesc>": 30539,
+  "<row": 30790,
+  "<row>": 30644,
+  "<runner": 30791,
+  "<runner>": 30645,
+  "<scopecontent": 30742,
+  "<scopecontent>": 30596,
+  "<separatedmaterial": 30743,
+  "<separatedmaterial>": 30597,
+  "<seriesstmt": 30686,
+  "<seriesstmt>": 30540,
+  "<sponsor": 30687,
+  "<sponsor>": 30541,
+  "<subarea": 30792,
+  "<subarea>": 30646,
+  "<subject": 30757,
+  "<subject>": 30611,
+  "<subtitle": 30688,
+  "<subtitle>": 30542,
+  "<table": 30793,
+  "<table>": 30647,
+  "<tbody": 30794,
+  "<tbody>": 30648,
+  "<tgroup": 30795,
+  "<tgroup>": 30649,
+  "<thead": 30796,
+  "<thead>": 30650,
+  "<title": 30758,
+  "<title>": 30612,
+  "<titlepage": 30797,
+  "<titlepage>": 30651,
+  "<titleproper": 30689,
+  "<titleproper>": 30543,
+  "<titlestmt": 30690,
+  "<titlestmt>": 30544,
+  "<unitdate": 30744,
+  "<unitdate>": 30598,
+  "<unitid": 30745,
+  "<unitid>": 30599,
+  "<unittitle": 30746,
+  "<unittitle>": 30600,
+  "<userestrict": 30747,
+  "<userestrict>": 30601,
+  "ABBR": 30970,
+  "ALIGN": 31015,
+  "ALTHEAD": 30971,
+  "ALTRENDER": 30972,
+  "ARCROLE": 31003,
+  "AUDIENCE": 30973,
+  "AUTHFILENUMBER": 30993,
+  "CALENDAR": 30994,
+  "CERTAINTY": 30974,
+  "CHAR": 31016,
+  "CHAROFF": 31017,
+  "COLNAME": 31018,
+  "COLNUM": 31019,
+  "COLS": 31020,
+  "COLSEP": 31021,
+  "COLWIDTH": 31022,
+  "CONTINUATION": 30975,
+  "COUNTRYCODE": 30976,
+  "COUNTRYENCODING": 30960,
+  "DATECHAR": 30977,
+  "DATEENCODING": 30961,
+  "ENCODINGANALOG": 30978,
+  "ENTITYREF": 31004,
+  "ERA": 30995,
+  "EXPAN": 30979,
+  "FINDAIDSTATUS": 30962,
+  "FRAME": 31023,
+  "FROM": 31005,
+  "HREF": 31006,
+  "ID": 31007,
+  "IDENTIFIER": 30963,
+  "LABEL": 30980,
+  "LANGCODE": 30996,
+  "LANGENCODING": 30964,
+  "LEVEL": 30981,
+  "LINKTYPE": 31008,
+  "MAINAGENCYCODE": 30982,
+  "MARK": 30983,
+  "MOREROWS": 31024,
+  "NAMEEND": 31025,
+  "NAMEST": 31026,
+  "NORMAL": 30997,
+  "NUMERATION": 30984,
+  "OTHERLEVEL": 30985,
+  "OTHERTYPE": 30986,
+  "PARENT": 31009,
+  "PGWIDE": 31027,
+  "PLACEMENT": 30987,
+  "PUBLICID": 30988,
+  "RELATEDENCODING": 30965,
+  "RENDER": 30989,
+  "REPOSITORYCODE": 30990,
+  "REPOSITORYENCODING": 30966,
+  "ROLE": 30998,
+  "ROWSEP": 31028,
+  "RULES": 30999,
+  "SCRIPTCODE": 31000,
+  "SCRIPTENCODING": 30967,
+  "SHOW": 31010,
+  "SOURCE": 31001,
+  "TARGET": 31011,
+  "TITLE": 31012,
+  "TO": 31013,
+  "TPATTERN": 31029,
+  "TYPECTUATE": 31002,
+  "UNIT": 30991,
+  "URL": 30968,
+  "URN": 30969,
+  "VALIGN": 31030,
+  "XMLNS": 30992,
+  "XPOINTER": 31014,
+  "abbr": 31041,
+  "althead": 31042,
+  "altrender": 31043,
+  "arcrole": 31059,
+  "authfilenumber": 31055,
+  "charoff": 31064,
+  "colname": 31065,
+  "colnum": 31066,
+  "cols": 31067,
+  "colsep": 31068,
+  "colwidth": 31069,
+  "countrycode": 31044,
+  "countryencoding": 31031,
+  "datechar": 31045,
+  "dateencoding": 31032,
+  "encodinganalog": 31046,
+  "entityref": 31060,
+  "expan": 31047,
+  "findaidstatus": 31033,
+  "href": 31061,
+  "identifier": 31034,
+  "langcode": 31056,
+  "langencoding": 31035,
+  "linktype": 31062,
+  "mainagencycode": 31048,
+  "morerows": 31070,
+  "nameend": 31071,
+  "namest": 31072,
+  "numeration": 31049,
+  "otherlevel": 31050,
+  "othertype": 31051,
+  "pgwide": 31073,
+  "publicid": 31052,
+  "relatedencoding": 31036,
+  "repositorycode": 31053,
+  "repositoryencoding": 31037,
+  "rowsep": 31074,
+  "scriptcode": 31057,
+  "scriptencoding": 31038,
+  "tpattern": 31075,
+  "typectuate": 31058,
+  "url": 31039,
+  "urn": 31040,
+  "valign": 31076,
+  "xmlns": 31054,
+  "xpointer": 31063
+}

special_tokens_map.json

@@ -0,0 +1,619 @@
+{
+  "additional_special_tokens": [
+    "<author>",
+    "<change>",
+    "<creation>",
+    "<descrules>",
+    "<ead>",
+    "<eadgrp>",
+    "<eadheader>",
+    "<eadid>",
+    "<edition>",
+    "<editionstmt>",
+    "<filedesc>",
+    "<frontmatter>",
+    "<langusage>",
+    "<notestmt>",
+    "<profiledesc>",
+    "<publicationstmt>",
+    "<publisher>",
+    "<revisiondesc>",
+    "<seriesstmt>",
+    "<sponsor>",
+    "<subtitle>",
+    "<titleproper>",
+    "<titlestmt>",
+    "<archdesc>",
+    "<archdescgrp>",
+    "<c>",
+    "<c01>",
+    "<c02>",
+    "<c03>",
+    "<c04>",
+    "<c05>",
+    "<c06>",
+    "<c07>",
+    "<c08>",
+    "<c09>",
+    "<c10>",
+    "<c11>",
+    "<c12>",
+    "<controlaccess>",
+    "<did>",
+    "<dsc>",
+    "<dscgrp>",
+    "<abstract>",
+    "<accessrestrict>",
+    "<accruals>",
+    "<acqinfo>",
+    "<altformavail>",
+    "<appraisal>",
+    "<archref>",
+    "<arrangement>",
+    "<bibliography>",
+    "<bibref>",
+    "<bioghist>",
+    "<container>",
+    "<custodhist>",
+    "<date>",
+    "<dimensions>",
+    "<extent>",
+    "<fileplan>",
+    "<langmaterial>",
+    "<legalstatus>",
+    "<materialspec>",
+    "<odd>",
+    "<originalsloc>",
+    "<origination>",
+    "<otherfindaid>",
+    "<physdesc>",
+    "<physfacet>",
+    "<physloc>",
+    "<phystech>",
+    "<prefercite>",
+    "<processinfo>",
+    "<relatedmaterial>",
+    "<repository>",
+    "<scopecontent>",
+    "<separatedmaterial>",
+    "<unitdate>",
+    "<unitid>",
+    "<unittitle>",
+    "<userestrict>",
+    "<corpname>",
+    "<famname>",
+    "<function>",
+    "<genreform>",
+    "<geogname>",
+    "<language>",
+    "<name>",
+    "<occupation>",
+    "<persname>",
+    "<subject>",
+    "<title>",
+    "<abbr>",
+    "<address>",
+    "<addressline>",
+    "<bibseries>",
+    "<blockquote>",
+    "<chronitem>",
+    "<chronlist>",
+    "<colspec>",
+    "<defitem>",
+    "<descgrp>",
+    "<div>",
+    "<emph>",
+    "<entry>",
+    "<event>",
+    "<eventgrp>",
+    "<expan>",
+    "<head>",
+    "<head01>",
+    "<head02>",
+    "<imprint>",
+    "<index>",
+    "<indexentry>",
+    "<item>",
+    "<label>",
+    "<lb>",
+    "<list>",
+    "<listhead>",
+    "<namegrp>",
+    "<note>",
+    "<num>",
+    "<p>",
+    "<row>",
+    "<runner>",
+    "<subarea>",
+    "<table>",
+    "<tbody>",
+    "<tgroup>",
+    "<thead>",
+    "<titlepage>",
+    "<arc>",
+    "<dao>",
+    "<daodesc>",
+    "<daogrp>",
+    "<daoloc>",
+    "<extptr>",
+    "<extptrloc>",
+    "<extref>",
+    "<extrefloc>",
+    "<linkgrp>",
+    "<ptr>",
+    "<ptrgrp>",
+    "<ptrloc>",
+    "<ref>",
+    "<refloc>",
+    "<resource>",
+    "<author",
+    "<change",
+    "<creation",
+    "<descrules",
+    "<ead",
+    "<eadgrp",
+    "<eadheader",
+    "<eadid",
+    "<edition",
+    "<editionstmt",
+    "<filedesc",
+    "<frontmatter",
+    "<langusage",
+    "<notestmt",
+    "<profiledesc",
+    "<publicationstmt",
+    "<publisher",
+    "<revisiondesc",
+    "<seriesstmt",
+    "<sponsor",
+    "<subtitle",
+    "<titleproper",
+    "<titlestmt",
+    "<archdesc",
+    "<archdescgrp",
+    "<c",
+    "<c01",
+    "<c02",
+    "<c03",
+    "<c04",
+    "<c05",
+    "<c06",
+    "<c07",
+    "<c08",
+    "<c09",
+    "<c10",
+    "<c11",
+    "<c12",
+    "<controlaccess",
+    "<did",
+    "<dsc",
+    "<dscgrp",
+    "<abstract",
+    "<accessrestrict",
+    "<accruals",
+    "<acqinfo",
+    "<altformavail",
+    "<appraisal",
+    "<archref",
+    "<arrangement",
+    "<bibliography",
+    "<bibref",
+    "<bioghist",
+    "<container",
+    "<custodhist",
+    "<date",
+    "<dimensions",
+    "<extent",
+    "<fileplan",
+    "<langmaterial",
+    "<legalstatus",
+    "<materialspec",
+    "<odd",
+    "<originalsloc",
+    "<origination",
+    "<otherfindaid",
+    "<physdesc",
+    "<physfacet",
+    "<physloc",
+    "<phystech",
+    "<prefercite",
+    "<processinfo",
+    "<relatedmaterial",
+    "<repository",
+    "<scopecontent",
+    "<separatedmaterial",
+    "<unitdate",
+    "<unitid",
+    "<unittitle",
+    "<userestrict",
+    "<corpname",
+    "<famname",
+    "<function",
+    "<genreform",
+    "<geogname",
+    "<language",
+    "<name",
+    "<occupation",
+    "<persname",
+    "<subject",
+    "<title",
+    "<abbr",
+    "<address",
+    "<addressline",
+    "<bibseries",
+    "<blockquote",
+    "<chronitem",
+    "<chronlist",
+    "<colspec",
+    "<defitem",
+    "<descgrp",
+    "<div",
+    "<emph",
+    "<entry",
+    "<event",
+    "<eventgrp",
+    "<expan",
+    "<head",
+    "<head01",
+    "<head02",
+    "<imprint",
+    "<index",
+    "<indexentry",
+    "<item",
+    "<label",
+    "<lb",
+    "<list",
+    "<listhead",
+    "<namegrp",
+    "<note",
+    "<num",
+    "<p",
+    "<row",
+    "<runner",
+    "<subarea",
+    "<table",
+    "<tbody",
+    "<tgroup",
+    "<thead",
+    "<titlepage",
+    "<arc",
+    "<dao",
+    "<daodesc",
+    "<daogrp",
+    "<daoloc",
+    "<extptr",
+    "<extptrloc",
+    "<extref",
+    "<extrefloc",
+    "<linkgrp",
+    "<ptr",
+    "<ptrgrp",
+    "<ptrloc",
+    "<ref",
+    "<refloc",
+    "<resource",
+    "</author>",
+    "</change>",
+    "</creation>",
+    "</descrules>",
+    "</ead>",
+    "</eadgrp>",
+    "</eadheader>",
+    "</eadid>",
+    "</edition>",
+    "</editionstmt>",
+    "</filedesc>",
+    "</frontmatter>",
+    "</langusage>",
+    "</notestmt>",
+    "</profiledesc>",
+    "</publicationstmt>",
+    "</publisher>",
+    "</revisiondesc>",
+    "</seriesstmt>",
+    "</sponsor>",
+    "</subtitle>",
+    "</titleproper>",
+    "</titlestmt>",
+    "</archdesc>",
+    "</archdescgrp>",
+    "</c>",
+    "</c01>",
+    "</c02>",
+    "</c03>",
+    "</c04>",
+    "</c05>",
+    "</c06>",
+    "</c07>",
+    "</c08>",
+    "</c09>",
+    "</c10>",
+    "</c11>",
+    "</c12>",
+    "</controlaccess>",
+    "</did>",
+    "</dsc>",
+    "</dscgrp>",
+    "</abstract>",
+    "</accessrestrict>",
+    "</accruals>",
+    "</acqinfo>",
+    "</altformavail>",
+    "</appraisal>",
+    "</archref>",
+    "</arrangement>",
+    "</bibliography>",
+    "</bibref>",
+    "</bioghist>",
+    "</container>",
+    "</custodhist>",
+    "</date>",
+    "</dimensions>",
+    "</extent>",
+    "</fileplan>",
+    "</langmaterial>",
+    "</legalstatus>",
+    "</materialspec>",
+    "</odd>",
+    "</originalsloc>",
+    "</origination>",
+    "</otherfindaid>",
+    "</physdesc>",
+    "</physfacet>",
+    "</physloc>",
+    "</phystech>",
+    "</prefercite>",
+    "</processinfo>",
+    "</relatedmaterial>",
+    "</repository>",
+    "</scopecontent>",
+    "</separatedmaterial>",
+    "</unitdate>",
+    "</unitid>",
+    "</unittitle>",
+    "</userestrict>",
+    "</corpname>",
+    "</famname>",
+    "</function>",
+    "</genreform>",
+    "</geogname>",
+    "</language>",
+    "</name>",
+    "</occupation>",
+    "</persname>",
+    "</subject>",
+    "</title>",
+    "</abbr>",
+    "</address>",
+    "</addressline>",
+    "</bibseries>",
+    "</blockquote>",
+    "</chronitem>",
+    "</chronlist>",
+    "</colspec>",
+    "</defitem>",
+    "</descgrp>",
+    "</div>",
+    "</emph>",
+    "</entry>",
+    "</event>",
+    "</eventgrp>",
+    "</expan>",
+    "</head>",
+    "</head01>",
+    "</head02>",
+    "</imprint>",
+    "</index>",
+    "</indexentry>",
+    "</item>",
+    "</label>",
+    "</lb>",
+    "</list>",
+    "</listhead>",
+    "</namegrp>",
+    "</note>",
+    "</num>",
+    "</p>",
+    "</row>",
+    "</runner>",
+    "</subarea>",
+    "</table>",
+    "</tbody>",
+    "</tgroup>",
+    "</thead>",
+    "</titlepage>",
+    "</arc>",
+    "</dao>",
+    "</daodesc>",
+    "</daogrp>",
+    "</daoloc>",
+    "</extptr>",
+    "</extptrloc>",
+    "</extref>",
+    "</extrefloc>",
+    "</linkgrp>",
+    "</ptr>",
+    "</ptrgrp>",
+    "</ptrloc>",
+    "</ref>",
+    "</refloc>",
+    "</resource>",
+    "COUNTRYENCODING",
+    "DATEENCODING",
+    "FINDAIDSTATUS",
+    "IDENTIFIER",
+    "LANGENCODING",
+    "RELATEDENCODING",
+    "REPOSITORYENCODING",
+    "SCRIPTENCODING",
+    "URL",
+    "URN",
+    "ABBR",
+    "ALTHEAD",
+    "ALTRENDER",
+    "AUDIENCE",
+    "CERTAINTY",
+    "CONTINUATION",
+    "COUNTRYCODE",
+    "DATECHAR",
+    "ENCODINGANALOG",
+    "EXPAN",
+    "LABEL",
+    "LEVEL",
+    "MAINAGENCYCODE",
+    "MARK",
+    "NUMERATION",
+    "OTHERLEVEL",
+    "OTHERTYPE",
+    "PLACEMENT",
+    "PUBLICID",
+    "RENDER",
+    "REPOSITORYCODE",
+    "UNIT",
+    "XMLNS",
+    "AUTHFILENUMBER",
+    "CALENDAR",
+    "ERA",
+    "LANGCODE",
+    "NORMAL",
+    "ROLE",
+    "RULES",
+    "SCRIPTCODE",
+    "SOURCE",
+    "TYPECTUATE",
+    "ARCROLE",
+    "ENTITYREF",
+    "FROM",
+    "HREF",
+    "ID",
+    "LINKTYPE",
+    "PARENT",
+    "SHOW",
+    "TARGET",
+    "TITLE",
+    "TO",
+    "XPOINTER",
+    "ALIGN",
+    "CHAR",
+    "CHAROFF",
+    "COLNAME",
+    "COLNUM",
+    "COLS",
+    "COLSEP",
+    "COLWIDTH",
+    "FRAME",
+    "MOREROWS",
+    "NAMEEND",
+    "NAMEST",
+    "PGWIDE",
+    "ROWSEP",
+    "TPATTERN",
+    "VALIGN",
+    "countryencoding",
+    "dateencoding",
+    "findaidstatus",
+    "identifier",
+    "langencoding",
+    "relatedencoding",
+    "repositoryencoding",
+    "scriptencoding",
+    "url",
+    "urn",
+    "abbr",
+    "althead",
+    "altrender",
+    "audience",
+    "certainty",
+    "continuation",
+    "countrycode",
+    "datechar",
+    "encodinganalog",
+    "expan",
+    "label",
+    "level",
+    "mainagencycode",
+    "mark",
+    "numeration",
+    "otherlevel",
+    "othertype",
+    "placement",
+    "publicid",
+    "render",
+    "repositorycode",
+    "unit",
+    "xmlns",
+    "authfilenumber",
+    "calendar",
+    "era",
+    "langcode",
+    "normal",
+    "role",
+    "rules",
+    "scriptcode",
+    "source",
+    "typectuate",
+    "arcrole",
+    "entityref",
+    "from",
+    "href",
+    "id",
+    "linktype",
+    "parent",
+    "show",
+    "target",
+    "title",
+    "to",
+    "xpointer",
+    "align",
+    "char",
+    "charoff",
+    "colname",
+    "colnum",
+    "cols",
+    "colsep",
+    "colwidth",
+    "frame",
+    "morerows",
+    "nameend",
+    "namest",
+    "pgwide",
+    "rowsep",
+    "tpattern",
+    "valign"
+  ],
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}