From f1f7842dd2ed110e9958f56d79ec504ae5d2bcd6 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Sat, 16 May 2020 18:40:26 -0700 Subject: crude djvu XML parsing --- tests/files/ERIC_ED441501_djvu.xml | 5142 ++++++++++++++++++++++++++++++++++++ tests/test_djvu_parse.py | 16 + 2 files changed, 5158 insertions(+) create mode 100644 tests/files/ERIC_ED441501_djvu.xml create mode 100644 tests/test_djvu_parse.py (limited to 'tests') diff --git a/tests/files/ERIC_ED441501_djvu.xml b/tests/files/ERIC_ED441501_djvu.xml new file mode 100644 index 0000000..a34967a --- /dev/null +++ b/tests/files/ERIC_ED441501_djvu.xml @@ -0,0 +1,5142 @@ + + + + + + + + + + + + +DOCUMENT +RESUME + + + + + + + + +ED +441 +501 + + + + + + + + +IR +057 +772 + + + + + + + + +AVAILABLE +FROM + + + + + + + + +PUB +TYPE + + +EDRS +PRICE + + +DESCRIPTORS + + + + + + + + +AUTHOR + + +TITLE + + +PUB +DATE + + +NOTE + + + + + + + + +IDENTIFIERS + + + + + + + + +Siripan, +Praditta + + + + +Metadata +and +Trends +of +Cataloging +in +Thai +Libraries +. + + +1999-08-00 + + + + +7p +. +; +In: +IFLA +Council +and +General +Conference. +Conference + + +Programme +and +Proceedings +(65th, +Bangkok, +Thailand, +August + + +20-28, +1999); +see +IR +057 +674. + + + + +For +full +text: + + + + +http +: +/ +/www. +if +la +. +org/lV/ +if +Ia65/papers/ll4-131e +. +htm. + + + + +Reports +- +Descriptive +(141) +- +- +Speeches +/Meeting +Papers +(150) + + + + +MFOl/PCOl +Plus +Postage. + + + + +*Cataloging; +Foreign +Countries; +Higher +Education; + + + + +Information +Services; +^Information +Technology; +Library + + +Education; +National +Programs; +*World +Wide +Web + + +Dublin +Core; +*Electronic +Resources; +International +Standards; + + +*Metadata; +Thailand + + + + + + + + +ABSTRACT + + + + + + + + +This +paper +reports +on +trends +in +cataloging +in +Thai + + + + + + + + +libraries, +focusing +on +the +use +of +information +technology +as +a +tool +to + + +accelerate +the +organization +of +resources, +the +benefit +of +cataloging +resources + + +available +from +the +Internet, +and +cataloging +policy +for +Internet +resources. + + + + +The +introduction +discusses +cataloging +Thai +documents, +managing +foreign + + +documents +and +CIP +(Cataloging +in +Publication) +, +and +USMARC +and +AACR2 + + +(Anglo-American +Cataloging +Rules, +2nd +edition) +, +An +overview +of +original + + +cataloging +tools +is +provided +in +the +second +section, +including +name +authority + + +files, +corporate +entry +list, +subject +headings +for +Thai +materials, +and +Thai + + +language +text +retrieval +software. +Cataloging +electronic +resources +is + + +described +in +the +third +section, +including +the +use +of +metadata +for +creating + + +World +Wide +Web +resources, +future +directions +toward +searchable +Web-based + + +information +service, +and +using +Dublin +Core. +The +fourth +section +addresses + + +shared +cataloging, +including: +Thai +List, +a +project +to +incorporate +university + + +library +catalogs +into +a +single, +national +bibliographic +database; +Journal + + +Link, +a +database +of +Web +sites +of +science +and +technology +journal +publishers; + + +the +National +library +and +the +National +Bibliography; +and +international + + +cooperation. +The +introduction +of +information +on +metadata +into +cataloging + + +courses +in +Thai +library +and +information +science +schools +is +noted +in +the +fifth + + +section. +(MES) + + + + + + + + +Reproductions +supplied +by +EDRS +are +the +best +that +can +be +made + + +from +the +original +document. + + + + + + + + + + + + + + + +jJ\0S?-77^ + + + + + + + + +http://www.ifla.Org/IV/ifla65/papers/l +14-131e.htm + + + + + + + + +Metadata +and +trends +of +cataloging +...nference +Programme +and +Proceedings + + + + + + + + + +mil + + + + + + + + + +IFLANET + + + + + + + + +Search +Contacts + + + + +Ifiternatjonal +Federatioii +of +Library +Associations +and +Institutions + + + + + + + + +Annual +Conference + + + + + + + + +65th +IFLA +Council +and +General + + +Conference + + + + +Bangkok, +Thailand, + + +August +20 +- +August +28, +1999 + + + + +Conference + + + + +Proceedings +- +— + + + + +Code +Number: +1 +14-13 +1-E + + +Division +Number: +IV + + +Professional +Group: +Cataloguing + + +Joint +Meeting +with: +- + + +Meeting +Number: +131 + + +Simultaneous +Interpretation: +No + + + + + + + + + +Metadata +and +trends +of +cataloging +in +Thai +libraries + + + + + + + + +Praditta +Siripan + + + + +Technical +Information +Access +Center + + + + +National +Science +& +Technology +Development +Agency + + + + +Bangkok, +Thailand + + + + + + + + +PERMISSION +TO +REPRODUCE +AND + + +DISSEMINATE +THIS +MATERIAL +HAS + + +BEEN +GRANTED +BY + + + + + + + + +A.L. +Van +Wesermael + + + + + + + + +TO +THE +EDUCATIONAL +RESOURCES + + + + +Abstract +, + + + + +A +status +of +cataloging +in +Thailand +shows +a +movement +toward +the +use +of +information + + +technology. +The +international +standards +for +cataloging +are +being +used +and +modified +to + + +effectively +organize +the +information +resources. +An +expanded +scope +of +resources +needed + + +cataloging +now +covers +cataloging +the +web +resources. +The +paper +mentions +Thailand +'s + + +participation +in +the +international +working +group +on +the +use +of +metadata +for +libraries. + + + + + + + + +ERIC + + + + + + + + +Paper + + + + + + + + +1 +. + + + + + + + + +2 +. + + + + + + + + +3. + + + + +4. + + + + + + + + +Introduction. + + + + +1.1 +Cataloging +Thai +documents. + + + + +1 +.2 +Managing +foreign +documents +and +CIP. + + + + +1.3 +U.S. +MARC +and +AACR +2 + + +Original +cataloging +tools. + + + + +2.1 +Personal +names +guides, + + + + +2.2 +Corporate +entry +authority +list. + + + + +2.3 +Thai +Subject +headings +. + + + + +2.4 +Thai +language +text +retrieval +software. + + + + +Cataloging +electronic +resources: +metadata +and +Dublin +Core +Initiative. + + +Shared +cataloging + + + + +4.1 +ThaiList. + + + + +4.2 +JoumalLink + + + + +4.3 +The +National +Library +and +the +National +Bibliography + + + + + + + + +U +S +DEPARTMENT +OF +EDUCATION + + + + +Office +of +Educational +Research +and +ImprovemetM + + + + +EDUCATIONAL +RESOURCES +INFORMATION + + +CENTER +(ERIC) + + + + +G +This +document +has +been +reproduced +as + + +received +from +the +person +or +organization + + +originating +it. + + + + +□ +Minor +changes +have +been +made +to + + +improve +reproduction +quality. + + + + + + + + +Points +of +view +or +opinions +stated +in +this + + +document +do +not +necessarily +represent + + +official +OERl +position +or +policy. + + + + + + + + +BEST +COPY +AVAILABLE + + + + + + + + +2 + + + + + + + + +1/6/00 +9:29 +AM + + + + + + + + + + + + + + + +Metadata +and +trends +of +cataloging +...nference +Programme +and +Proceedings + + + + + + + + +http://www.ifla.org/IV/ifla65/papers/114-131e.htm + + + + + + + + +4.4 +International +cooperation + + + + +5. +Library +education. + + + + +6. +Conclusion. + + + + +1. +Introduction. + + + + +The +libraries +in +Thailand +have +a +dual +responsibility +in +cataloging +: +Foreign +and +Thai +materials. + + +Most +libraries +are +using +the +Library +of +Congress +and +Dewey +Decimal +Classification. +The +U.S. + + +MARC +and +AACR2 +are +commonly +adapted +to +implement +by +the +computerized +libraries, + + +particularly +by +the +academic +and +special +libraries. +The +integrated +library +system +and +the +access + + +to +the +international +cataloging +services +such +as +the +OCLC's +and +cataloged +data +from +OP +AC + + +that +are +available +from +the +Internet +as +well +as +the +data +from +CIP +- +Cataloging +in +Publications + + +have +facilitated +a +great +deal +Thai +librarians' +routine +cataloging +work. +Cataloging +our +local + + +resources +revealed +some +difficulty +yet +rather +challenging. +Thai +catalogers +faced +with +such + + +problems +as +insufficient +classification +numbers +for +Thai +subjects, +and +the +subject +headings +do + + +not +provide +terms +for +local +use. +For +computerized +systems, +Thai +libraries +have +difficulty +in +text + + +retrieval +of +the +data +written +in +the +Thai +language +as +well +as +in +data +inputting +because +the +Thai + + +OCR +- +Optical +Character +Recognition +level +of +performance +is +still +not +satisfactory. +Leadership + + +in +cataloging +research +in +Thailand +is +the +Subcommittee +on +Technical +Services +and +the + + +Subcommittee +on +Information +Technology +under +the +Academic +Libraries' +Cooperation + + +Committee. +The +projects +are +compilation +of +Thai +subject +headings, +an +authority +list +of +Thai + + +corporate +names +(government +offices +and +state +enterprises), +and +the +Thai +translation +of +U.S. + + +MARC +and +AACR2. + + + + +This +paper +reports +on +the +trends +of +cataloging +in +Thai +libraries, +with +an +interest +in +the +use +of + + +the +information +technology +as +tools +to +accelerate +the +organization +of +resources, +the +benefit +of + + +cataloging +resources +available +from +the +Internet, +and +the +discussion +on +cataloging +policy +for + + +the +Internet +resources. + + + + +1.1 +Cataloging +Thai +documents. +A +fast +development +in +the +use +of +IT +in +Thai +libraries + + +have +reflected +enormously +the +increased +need +to +use +the +libraries +by +the +students, + + +academic +and +researchers. +Thai +users +have +relied +on +the +imported +information +resources + + +from +foreign +vendors +and +publishers +for +a +long +time +(with +the +exception +to +the +Thai + + +language +collections, +which +have +served +the +Thai +library +users +by +the +manual +and +OP +AC + + +searching). +Local +information +received +relatively +less +attention +in +terms +of +database + + +development +despite +the +importance +of +the +Thai +government +documents, +manuscripts + + +and +rare +books, +complementary +memoirs +for +the +deaths, +Buddhist +teaching +and +history + + +that +represent +a +unique +collection +of +Thai +information. +These +collections +need +original + + +cataloging +. +The +best +way +to +access +the +Thai +information +now +is +to +search +the +libraries' + + +OP +AC +from +the +National +Library +of +Thailand, +and +to +search +the +Thai +academic + + +libraries'OPAC +from +the +Internet. +But +, +because +most +Thai +information +were +published + + +in +the +Thai +language, +users +can +access +the +Thai +language +computerized +catalogs +by + + +downloading +the +Thai +fonts +from +Netscape +and +Internet +Explorer +to +be +able +to +read +the + + +message +displayed +on +the +screen. +But +searching +is +however +limited +to +terminals +with +the + + +Thai +character +keyboards. + + + + +1.2 +Managing +foreign +documents +and +CIP. +All +Thai +libraries +purchase +a +number +of + + +foreign +books +that +need +cataloging. +It +is +simple +enough +for +many +libraries +that + + +subscribed +to +OCLC +catalogs +to +just +retrieve +the +cataloging +data +for +the +acquired +books + + +and +add +the +data +to +their +records. +Some +libraries +retrieved +the +cataloging +data +such +as +the + + +classification +numbers +and +subject +headings +from +other +libraries's +OP +AC. +There +is +a + + +number +of +libraries +that +do +not +have +access +to +the +Internet +and +need +to +catalog +and +to +use + + +the +CIP +for +creating +their +catalog +records. + + + + +1.3 +U.S. +MARC +and +AACR +2. +Thai +libraries +have +accepted +the +international +Standards: + + +the +U.S. +MARC +and +the +Anglo +American +Cataloging +Rules +for +cataloging +both +Thai +and + + +foreign +materials +with +necessary +modifications. + + + + +O + + + + +ERIC + + + + + + + + +1/6/00 +9:29 +AM + + + + + + + + + + + + + + + +Metadata +and +trends +of +cataloging +...nference +Programme +and +Proceedings + + + + + + + + +http://www.ifla.Org/IV/ifla65/papers/l +14-131e.htm + + + + + + + + +2. +Original +cataloging +tools + + + + +2.1 +Name +authority +files. +Thai +names +have +their +own +characteristics. +Persons +are + + +recognized +by +their +first +names +and +not +the +last +names +nor +the +family +names. +There +are + + +personal +names +with +royal +titles +and +with +titles +of +nobility +as +well +as +names +with + + +religious +ranks. +The +National +Library +of +Thailand +is +responsible +for +compilation +of +the + + +guide +to +use +the +Thai +personal +names. +0} + + + + +2.2 +Corporate +entry +list. +A +Cataloging +Librarians +Working +Group +under +the + + +Subcommittee +on +the +Academic +Libraries +Cooperation +published +the +second +and +revised + + +1998 +edition +of" +A +List +of +Thai +Government +and +State +Enterprise +Entries +for +Cataloging + + +the +Thai +Language +Materials +". +The +electronic +list +is +planned +to +be +available +from +Thai + + +academic +libraries' +Web +sites +in +the +near +future. +(2} + + + + +2.3 +Subject +headings +for +Thai +Materials. +Most +Thai +libraries +use +the +Thai +Library + + +Association +Subject +Headings, +Library +of +Congress +Subject +Headings, +Sears +List +of + + +Subject +Headings, +and +the +subject +authority +list +compiled +by +the +Cataloging +Librarians + + +Working +Group +under +the +Subcommittee +on +the +Academic +Libraries +Cooperation. +The + + +group +meets +every +two +months +to +work +on +the +added +new +headings +for +incorporation + + +with +the +existing +list. +{3} +For +specialized +subject +headings, +the +Library +and +Information + + +Center +of +the +Bank +of +Thailand +compiled +a +Thesaurus +of +Finance +and +Banking +terms +for + + +their +use +in +cataloging +the +Thai +materials. +The +Siam +Cement +Information +Center + + +constructed +a +thesaurus +of +Building +and +Construction +Materials +for +use +with +their + + +in-house +specialized +database. +Water +Buffaloes +Thesaurus +was +compiled +by +Kasetsart + + +University +Main +Library +for +the +database +run +by +Kasetsart +International +Buffalo + + +Information +Center. +The +Thai +Culture +Thesaurus +was +the +only +thesaurus +created +in +the + + +Thai +language, +by +the +Office +of +the +National +Committee +on +the +Thai +Culture. +At +present + + +a +common +use +of +tools +for +subject +indexing +is +by +manual +process. +Only +a +few +libraries + + +started +to +install +the +thesaurus +list +in +the +system +in +electronic +format. + + + + +2.4 +Thai +language +text +retrieval +software. +A +status +of +cataloging +the +Thai +language + + +Materials +depend +on +manual +indexing. +The +automatic +indexing +for +full-text +search +for + + +the +Thai +language +requires +a +lot +more +research +still, +in +order +to +solve +several +problems + + +such +as +the +appropriate +word +breaking, +and +the +effective +use +of +operators +for +limiting +and + + +expanding +the +search. +The +written +Thai +language +has +some +special +characteristics, +for + + +example +the +way +the +language +is +written +without +word-breaks, +and +there +is +no +sign +when + + +sentences +end. +Besides, +syllable +breaking +in +words +can +cause +mistakes +of +meaning +in + + +truncated +searching +the +problems +have +results +in +a +number +of +backlog, +non-catalogued + + +materials. +In +August +1999, +a +revised +version +of +full-text +search +engine +developed +for +use + + +with +the +Thai +and +English +language +databases +is +due +to +be +completed +by +the +technical + + +team +of +Technical +Information +Access +Center +(TIAC). +This +will +result +in +the +improved + + +full-text +searching +for +precatalogued +materials, +before +controlled +terms +indexing +can +be + + +completed. + + + + +3. +Cataloging +electronic +resources: +metadata +and +Dublin +Core +Initiative. + + + + +Thai +libraries +provide +a +growing +number +of +electronic +resources. +A +concept +of +digital +libraries + + +has +encouraged +many +libraries +to +implement +the +electronic +library +and +information +services + + +more +seriously. +Access +to +the +universities' +OP +AC +has +become +widely +available +throughout +the + + +country +while +a +number +of +special +libraries +of +the +government +allow +the +public +to +search +their + + +library +collections +by +the +Internet +access. +Through +the +government's +homepages, +the +public +is + + +able +to +receive +the +important +information +more +easily. +And +this +means +a +number +of + + +government +publications +have +been +distributed +on +the +www, +from +the +libraries +and +from +other + + +information +services. +In +general +the +information +was +prepared +by +using +HTML +and +the + + +commonly +available +browsers, +however +only +a +few +Web +sites +created +meta +tags +for +the + + + + + + + + +ERIC + + + + + + + + +4 + + + + + + + + +1/6/00 +9:29 +AM + + + + + + + + + + + + + + + +http://www.ifla.org/IV/ifla65/papers/114-131e.htm + + + + + + + + +Metadata +and +trends +of +cataloging +...nference +Programme +and +Proceedings + + + + + + + + +databases. +To +give +the +example +of +the +tables +of +content +service +for +subscribed +journals, + + +libraries +now +image-scanned +the +content +pages +and +distributed +them +on +their +web +sites. +Users + + +can +browse +but +search +the +current +contents +of +their +new +journals. + + + + +3.1 +The +use +of +metadata +for +creating +www +resources. +It +is +interesting +to +note +the +Fact + + +that +traditional +database +searching +gave +different +results +from +web +browsing. +A +few +Thai + + +libraries +namely +King +Mongkut +Institute +of +Technology +North +Bangkok +and +Technical + + +Information +Access +Center +(TIAC) +realize +the +need +to +create +effective, +searchable + + +databases +so +that +users +can +benefit +the +most +from +searching +their +databases +and +without + + +having +to +spend +long +time +browsing +and +discovering +irrelevant +information. +TIAC + + +library +created +the +databases +using +HTML +and +commercial +software +(Microsoft + + +Access™) +in +conversion +of +the +data +prepared +with +meta +tags +for +the +data +structure. +The + + +available +tools +from +the +Internet +Information +Server +and +SQL +are +used +to +enable +free +text + + +searching +in +English +and +in +Thai. +(4) +Librarians +preferred +to +serve +their +users +with +the + + +structured +databases +for +web-based +searching, +but +the +methods +require +some +professional + + +knowledge +and +training +in +computer +programming. +Thai +libraries, +which +do +not +have + + +technical +support +from +the +computer +programmers, +can +manage +to +develop +the +databases + + +at +very +limited +extent. + + + + +3.2 +Future +directions +toward +searchable +web-based +information +service. +Special + + +Collections +of +digitized +information +will +be +managed +more +and +more +by +the +libraries. +A + + +National +Science +and +Technology +Development +Agency +- +NSTDA's +planned +S&T + + +Information +Resource +Center +aimed +to +create +the +database +of +web +resources +using +the + + +standard +metadata, +Dublin +Core, +with +RDF +and +XML. +Another +project +under +study +is +the + + +Asian +Institute +of +Technology's +graduate +student +thesis +on +multiple +language +database +of + + +digital +theses. +Chulalongkom +University +has +also +made +another +pioneer +movement +that + + +the +university +information +resources +will +be +produced +more +in +a +digital +based. +The + + +university +libraries +then +will +extend +the +responsibility +to +cover +the +management +of + + +access +to +web +resources. +The +Centers +of +Academic +Resources +(CAR) +of +Chulalongkom + + +University +has +joined +the +OCLC's +CORC +Project +after +having +realized +the +need +for +well + + +organized +information +resources +available +from +the +Internet. +The +beginning +era +of + + +Chulalongkom's +second +century +means +also +a +change +into +a +web-based +educational + + +system, +a +virtual +library +and +the +electronic +scholarly +communications. +CAR +announced + + +the +plan +for +the +next +decade +that +she +will +lead +the +faculty, +researchers +and +students +to + + +develop +the +futvue +information +resources. +Metadata +and +other +standards +for +creating + + +digital +information +will +be +the +task +that +CAR +takes +as +her +responsibility +to +inform +and +to + + +train +people +within +the +university. +(5} + + + + +3.3 +Using +Dublin +Core. +Technical +Information +Access +Center, +National +Science +and + + +Technology +Development +Agency +(TIAC/NSTDA) +has +participated +in +the +Dublin +Core + + +Metadata +Working +Group +since +1996. +A +translation +of +the +Dublin +Core +15 +Elements +into + + +the +Thai +language +was +completed +and +registered +with +the +multiple +languages +Dublin + + +Core +Working +Group. +Technical +Information +Access +Center, +Kasetsart +University, + + +and +Asian +Institute +of +Technology +and +Chulalongkom +University +organized +four + + +workshops +on +metadata +and +Dublin +Core +Initiatives +in +Thailand. +The +library + + +communities +began +to +discuss +a +need +of +training +on +database +creation +using +metadata + + +and +Dublin +Core. +It +is +interesting +to +note +the +collaboration +works +of +the +academic + + +librarians +under +the +Subcommittee +on +the +Academic +Libraries +Cooperation +especially + + +the +work +of +the +cataloging +librarians +who +have +spent +years +after +years +constmcting +tools + + +needed +for +good +cataloging +such +as +the +authority +lists +of +Thai +names +and +Thai +subject + + +headings. +Their +work +will +be +available +in +the +electronic +format +for +facilitated +use +with + + +machine-readable +cataloging +by +Thai +librarians +and +by +other +creators +of +information +in + + +other +countries +who +are +interested +to +learn +the +Thai +studies. +Cataloging +practice +will +be + + +able +to +use +such +created +tools +more +easily +in +managing +library +information +in +electronic + + +form. + + + + + + + + +O + + + + +ERIC + + + + +hfiiinnigiifniaaaa + + + + +H +U1 +O + + + + + + + + +4. +Shared +cataloging: + + + + + + + + +5 + + + + + + + + +1/6/00 +9:29 +AM + + + + + + + + + + + + + + + +Metadata +and +trends +of +cataloging +...nference +Programme +and +Proceedings + + + + + + + + +http://www.ifla.Org/IV/ifla65/papers/l +14-131 +e.htm + + + + + + + + +Libraries +have +for +a +long +time +attempted +to +establish +a +Cooperative +cataloging +in +order +to +avoid + + +duplication +of +effort +that +several +libraries +have +to +catalog +the +same +titles +uneconomically. + + +Sharing +the +catalogued +materials +now +means +more +than +reduced +duplicated +efforts +but +also + + +sharing +the +investment +cost +through +shared +collections +from +virtual +access +of +libraries + + +throughout +the +country. + + + + +4.1 +Thai +List. +The +Bureau +of +University +Affairs +has +initiated +a +project +to +Incorporate +the + + +university +library +catalogs +- +OP +AC +into +a +single, +national +bibliographic +databases. +{7} + + + + +All +the +public +universities +will +access +the +resources, +books +and +journals +as +well +as + + +audio-visual +materials +and +CD-ROM +databases +from +a +single +search. +Planning +for +the + + +operational +project +involves +the +integration +of +the +various +types +of +computer +technology, + + +the +universal +intellectual +property +rights, +and +the +methods +of +delivery +service +and + + +suitable +payment +schemes +as +well +as +professional +training. + + + + +4.2 +Journal +Link +is +a +database +of +a +list +of +web +sites +of +science +and +technology +journal + + +publishers +compiled +by +the +library +of +the +Faculty +of +Science, +Chulalongkom +University. + + +Included +in +the +database +is +a +union +list +of +science +and +technology +journals +in +Thai + + +libraries. +Journal +Link +opens +for +the +science +libraries +to +join +its +membership +and +to +be + + +able +to +search +the +database +freely +from +the +Internet. +Members +can +also +update +their +own + + +journal +holdings +through +a +decentralized +network +from +the +Internet +. +This +initiative +is + + +very +useful +for +the +interlibrary +loan +and +for +document +delivery +service. +Resources +from + + +science +journals +can +be +located +and +updated +more +quickly +and +shared +more +widely. + + +Journal +Link's +movement +in +the +future +is +to +offer +the +table +of +content +service, +and + + +members +will +be +able +to +order +full +articles +and +payment +can +be +processed +by +the + + +electronic +process. + + + + +4.3 +The +National +Library +and +the +National +Bibliography. +The +National +Libraiy +of + + +Thailand +is +in +charge +of +national +bibliographic +control. +It +is +by +law +a +depository +library + + +of +all +books +and +journals +published +in +Thailand. +OPAC +searching +is +available +for +service + + +at +the +National +Library +in +Bangkok +and +from +branches +in +the +provinces. +An +awareness +of + + +the +Thai +Internet +resources +has +been +noted, +but +the +movement +into +the +organizing +access + + +to +the +available +web +resources +by +using +the +metadata, +by +the +National +Library +is +still +in + + +an +initial +stage. + + + + +4.4 +International +cooperation. +Indexing +Thai +materials +is +technically +difficult +and + + +costly +for +foreign +libraries. +The +language +barrier, +and +insufficient +reference +tools +for + + +indexing +has +encouraged +a +consortium +of +Southeast +Asian +Studies +librarians +overseas +to + + +seek +for +cooperative +indexing +project +with +Thai +libraries. +A +cooperation +between + + +Technical +Information +Access +Center +(TIAC) +and +the +University +of +Washington +is +one + + +of +the +Thai +indexing +projects +that +is +planned +to +be +operate +as +a +database +using +the +Dublin + + +Core +Metadata +Elements. +(9) +The +database +will +be +a +case +study +of +shared +cataloging +and + + +indexing +by +using +the +expertise +of +the +Thai +librarians, +and +the +technology +provided +by + + +the +U.S. +library. +Users +from +both +parties +can +access +more +information, +faster +and +more + + +accurately. + + + + +5. +Library +education. + + + + + + + + +o + + + + +ERIC + + + + + + + + +The +current +cataloging +courses +offered +by +the +library +and +information +science +schools +in + + +Thailand +do +not +yet +offer +specifically +teaching +in +the +digital +libraries, +metadata +and + + +organization +of +web +resources. +Some +courses +on +information +storage +and +retrieval +cover +the + + +evaluation +methods +of +the +databases +searching +analysis +and +the +issues +on +the +use +of +metadata + + +were +introduced +to +the +students. +The +schools +of +library +and +information +science +at + + +Chulalongkom +University, +Chiang +Mai +University +and +Sukhothai +Thammatirat +Open + + +University +included +a +new +topic +on +metadata +for +cataloging +library +resources. +The +metadata + + +concept +has +also +been +introduced +to +the +Information +Technology +courses +offered +by +the +Asian + + +Institute +of +Technology, +Mahidol +University, +and +Kasetsart +University. + + + + + + + + +6 + + + + + + + + +1/6/00 +9:29 +AM + + + + + + + + + + + + + + + +Metadata +and +trends +of +cataloging +...nference +Programme +and +Proceedings + + + + + + + + +http://www.ifIa.org/IV/ifla65/papers/114-131e.htm + + + + + + + + +6. +Conclusion. + + + + +A +fast +movement +of +the +IT +world +has +caused +the +"On +Site +Libraries" +or +the +"Physical + + +Libraries" +a +so-called +threat +as +to +be +removed +or +replaced +by +the +"Digital +Libraries." +Thai + + +librarians +began +to +feel +the +impact +from +the +changes. +First, +the +new +integrated +library +system + + +forced +librarians +to +learn +new +technology +and +to +become +computer +literate. +Then, +in +the + + +Internet +world, +library +users +began +to +look +for +the +information +they +need +by +browsing +the + + +cyberspace. +People +said +that +" +Digital +Libraries +will +replace +the +paper +libraries", +"nobody + + +needs +to +go +to +the +libraries", +and +"everything +is +accessible +from +homes +via +the +Internet". + + +Ironically, +however, +the +concept +of +metadata +and +digital +libraries +reflected +the +fundamental + + +knowledge +of +librarianship. +Discussion +on +organized +access +to +the +digital +resources + + +emphasizes +the +simplicity, +and +the +interoperability +of +universal +implementation. +The + + +International +library +community +discussed +all +the +topics, +and +many +problems +were +solved. + + +Librarians +can +see +the +new +look +of +libraries +in +the +digital +form. +But, +librarians' +job +is +never + + +changed. +Librarians +must +provide +digital +library +resources, +catalog +them, +and +teach +users +to + + +find +the +right +information +from +the +digital +libraries. + + + + +Endnotes + + + + +1. +The +National +Library +of +Thailand +. +A +Table +for +Cataloging +Thai +Authors. +Bangkok, +N.D. + + + + +2. +Subcommittee +on +the +Academic +Libraries +Cooperation. +A +report +of +the +Cataloging +Working + + +Group +presented +at +the +annual +conference +on +the +Academic +Libraries +Cooperation. +Chiang + + +Mai, +Mae +Jo +University, +1998. +(In +Thai) + + + + +3. +Subcommittee +on +the +Academic +Libraries +Cooperation. +A +report +of +the +Cataloging +Working + + +Group +presented +at +the +annual +conference +on +the +Academic +Libraries +Cooperation. +Chiang + + +Mai, +Mae +Jo +University, +1998. +(In +Thai) + + + + +4. +Technical +Information +Access +Center. +(http://www.tiac.or.thI + + + + +5. +Chulalongkom +University. +Centers +for +the +Academic +Resources. +A +draft +plan +for +library +and + + +information +policy +for +the +implementation +of +Chulalongkom +University +Plan +for +Year +2000. + + +Bangkok, +1999. +(An +interview). + + + + +6. +A +Thai +translation +of +the +Dublin +Core +15 +Elements +(http://www.tiac.or.th) + + + + +7. +Subcommittee +on +the +Academic +Libraries +Cooperation. +A +report +from + + +the +annual +conference +on +the +Academic +Libraries +Cooperation. +Chiang +Mai, + + + + +Mae +Jo +University, +1998. +(In +Thai). + + + + +8. +Chulalongkom +University. +Faculty +of +Science +Library. +Journal +Link + + +(http://'www.sc.chula.ac.thl + + + + +9. +An +agreement +in +process +for +approval +by +the +University +of +Washington +and +Technical + + +Information +Access +Center. +1999. + + + + + + + + +Latest +Revision: +July +8. +1999. +Copyright +© +1995-1999 + + + + +International +Federation +of +Library +Associations +and +Institutions + + + + +www.ifla.org + + + + + + + + +ERIC + + + + + + + + +V +Ui +\J + + + + + + + + +1 + + + + + + + + +1/6/00 +9:29 +AM + + + + + + + + + + + + + + + +U.S. +Department +of +Education + + + + +Office +of +Educational +Research +and +Improvement +(OERI) + + +National +Library +of +Education +(NLE) + + +Educational +Resources +Information +Center +(ERIC) + + + + + + + + +® + + + + + + + + + +NOTICE + + + + +PFPRODUrTTON +BASIS + + + + + + + + +This +document +is +covered +by +a +signed +“Reproduction +Release + + +(Blanket) +form +(on +file +within +the +ERIC +system), +encompassing +all + + +or +classes +of +documents +from +its +source +organization +and, +therefore, + + +does +not +require +a +“Specific +Document” +Release +form. + + + + + + + + +This +document +is +Federally-funded, +or +carries +its +own +permission +to + + +reproduce, +or +is +otherwise +in +the +public +domain +and, +therefore, +may + + +be +reproduced +by +ERIC +without +a +signed +Reproduction +Release +form + + +(either +“Specific +Document” +or +“Blanket”). + + + + + + + + +( +9 +/ +97 +) + + + + + + + + + + diff --git a/tests/test_djvu_parse.py b/tests/test_djvu_parse.py new file mode 100644 index 0000000..66c2804 --- /dev/null +++ b/tests/test_djvu_parse.py @@ -0,0 +1,16 @@ + +from io import StringIO +from fatcat_scholar.djvu import djvu_extract_leaf_texts + + +def test_djvu_extract_leaf_texts(): + + # https://archive.org/details/ERIC_ED441501 + with open('tests/files/ERIC_ED441501_djvu.xml', 'r') as f: + blob = f.read() + + leaves = djvu_extract_leaf_texts(StringIO(blob), [3,6]) + assert 3 in leaves + assert 6 in leaves + assert "2. Original cataloging tools" in leaves[3] + assert len(leaves) == 2 -- cgit v1.2.3