charconv.sgm

harvest是一个下载html网页得机器人

<!-- ============================================================= -->
<!-- MODULE:    Character to Entity Specification                  -->
<!-- VERSION:   3.0 (Morgan Cundiff and Randll Barry)                                   -->
<!-- DATE:      June 18, 2001                                  -->
<!--                                                               -->
<!-- MULBERRY INTERNAL VERSION CONTROL:                            -->
<!-- $Id: charconv.sgm,v 1.1 2002/12/16 13:26:06 adam Exp $         -->
<!-- ============================================================= -->

<!-- ============================================================= -->
<!-- SYSTEM:    MARC <-> SGML <-> XML Conversion                           -->
<!--                                                               -->
<!-- PURPOSE:   Define relationships between MARC Extended Latin   -->
<!--            character set, character numbers, SGML entities    -->
<!--            and XML entities.                                  -->
<!--                                                               -->
<!-- CONTAINS:  SGML Document conforming to the Character-Entity   -->
<!--            Map File DTD                                       -->
<!--                                                               -->
<!-- MODULES REQUIRED:                                             -->
<!--            None                                               -->
<!--                                                               -->
<!-- CREATED FOR:                                                  -->
<!--            MARC Standards Office                              -->
<!--                                                               -->
<!-- ORIGINAL CREATION DATE:                                       -->
<!--            October 1997                                       -->
<!--                                                               -->
<!-- CREATED BY:                                                   -->
<!--            Mulberry Technologies, Inc. (TKG)                  -->
<!--            17 West Jefferson Street, Suite 207                -->
<!--            Rockville, MD  20850  USA                          -->
<!--            Phone:  [phone]                            -->
<!--            Fax:    [phone]                            -->
<!--            e-mail: [e-mail]                      -->
<!--            WWW:    http://www.mulberrytech.com                -->
<!-- ============================================================= -->
<entitymap>
<character hex="E2 41" dec="226 065"><isoentity>Aacute</isoentity><desc>latin capital letter a with acute</desc><unientity>00C1</unientity></character>
<character hex="E2 61" dec="226 097"><isoentity>aacute</isoentity><desc>latin small letter a with acute</desc><unientity>00E1</unientity></character>
<character hex="E2 E6 41" dec="226 230 065"><isoentity>Abreveac</isoentity><desc>latin capital letter a with breve and acute</desc><unientity>1EAE</unientity></character>
<character hex="E2 E6 61" dec="226 230 096"><isoentity>abreveac</isoentity><desc>latin small letter a with breve and acute</desc><unientity>1EAF</unientity></character>
<character hex="E6 F2 41" dec="230 242 065"><isoentity>Abrevedb</isoentity><desc>latin capital letter a with breve and dot below</desc><unientity>1EB6</unientity></character>
<character hex="E6 F2 61" dec="230 242 097"><isoentity>abrevedb</isoentity><desc>latin small letter a with breve and dot below</desc><unientity>1EB7</unientity></character>
<character hex="E1 E6 41" dec="225 230 065"><isoentity>Abrevegr</isoentity><desc>latin capital letter a with breve and grave</desc><unientity>1EB0</unientity></character>
<character hex="E1 E6 61" dec="225 230 097"><isoentity>abrevegr</isoentity><desc>latin small letter a with breve and grave</desc><unientity>1EB1</unientity></character>
<character hex="E0 E6 41" dec="224 230 065"><isoentity>Abreveha</isoentity><desc>latin capital letter a with breve and hook above</desc><unientity>1EB2</unientity></character>
<character hex="E0 E6 61" dec="224 230 097"><isoentity>abreveha</isoentity><desc>latin small letter a with breve and hook above</desc><unientity>1EB3</unientity></character>
<character hex="E4 E6 41" dec="228 230 065"><isoentity>Abreveti</isoentity><desc>latin capital letter a with breve and tilde</desc><unientity>1EB4</unientity></character>
<character hex="E4 E6 61" dec="228 230 097"><isoentity>abreveti</isoentity><desc>latin small letter a with breve and tilde</desc><unientity>1EB5</unientity></character>
<character hex="E6 41" dec="230 065"><isoentity>Abreve</isoentity><desc>latin capital letter a with breve</desc><unientity>0102</unientity></character>
<character hex="E6 61" dec="230 097"><isoentity>abreve</isoentity><desc>latin small letter a with breve</desc><unientity>0103</unientity></character>
<character hex="E9 41" dec="233 065"><isoentity>Acaron</isoentity><desc>latin capital letter a with caron</desc><unientity>01CD</unientity></character>
<character hex="E9 61" dec="233 097"><isoentity>acaron</isoentity><desc>latin small letter a with caron</desc><unientity>01CE</unientity></character>
<character hex="E3 E2 41" dec="227 226 065"><isoentity>Acircac</isoentity><desc>latin capital letter a with circumflex and acute</desc><unientity>1EA4</unientity></character>
<character hex="E3 E2 61" dec="227 226 097"><isoentity>acircac</isoentity><desc>latin small letter a with circumflex and acute</desc><unientity>1EA5</unientity></character>
<character hex="E3 F2 41" dec="227 242 065"><isoentity>Acircdb</isoentity><desc>latin capital letter a with circumflex and dot below</desc><unientity>1EAC</unientity></character>
<character hex="E3 F2 61" dec="227 242 097"><isoentity>acircdb</isoentity><desc>latin small letter a with circumflex and dot below</desc><unientity>1EAD</unientity></character>
<character hex="E3 E1 41" dec="227 225 065"><isoentity>acircgr</isoentity><desc>latin capital letter a with circumflex and grave</desc><unientity>1EA6</unientity></character>
<character hex="E3 E1 61" dec="227 225 097"><isoentity>acircgr</isoentity><desc>latin small letter a with circumflex and grave</desc><unientity>1EA7</unientity></character>
<character hex="E3 E0 41" dec="227 224 064"><isoentity>Acircha</isoentity><desc>latin capital letter a with circumflex and hook above</desc><unientity>1EA8</unientity></character>
<character hex="E3 E0 61" dec="227 224 097"><isoentity>acircha</isoentity><desc>latin small letter a with circumflex and hook above</desc><unientity>1EA9</unientity></character>
<character hex="E4 E3 41" dec="228 227 065"><isoentity>Acircti</isoentity><desc>latin capital letter a with circumflex and tilde</desc><unientity>1EAA</unientity></character>
<character hex="E4 E3 61" dec="228 227 097"><isoentity>acircti</isoentity><desc>latin small letter a with circumflex and tilde</desc><unientity>1EAB</unientity></character>
<character hex="E3 41" dec="227 065"><isoentity>Acirc</isoentity><desc>latin capital letter a with circumflex</desc><unientity>00C2</unientity></character>
<character hex="E3 61" dec="227 097"><isoentity>acirc</isoentity><desc>latin small letter a with circumflex</desc><unientity>00E2</unientity></character>
<character hex="E2" dec="226"><isoentity>acute</isoentity><desc>combining acute accent</desc><unientity>0301</unientity></character>
<character hex="E5 E7 41" dec="229 231 065"><isoentity>Adotama</isoentity><desc>latin capital letter a with dot above and macron</desc><unientity>01E0</unientity></character>
<character hex="E5 E7 61" dec="229 231 097"><isoentity>adotama</isoentity><desc>latin small letter a with dot above and macron</desc><unientity>01E1</unientity></character>
<character hex="F2 41" dec="242 065"><isoentity>Adotb</isoentity><desc>latin capital letter a with dot below</desc><unientity>1EA0</unientity></character>
<character hex="F2 61" dec="242 097"><isoentity>adotb</isoentity><desc>latin small letter a with dot below</desc><unientity>1EA1</unientity></character>
<character hex="E7 41" dec="231 065"><isoentity>Adot</isoentity><desc>latin capital letter a with dot above</desc><unientity>0226</unientity></character>
<character hex="E7 61" dec="231 097"><isoentity>adot</isoentity><desc>latin small letter a with dot above</desc><unientity>0227</unientity></character>
<character hex="E2 A5" dec="226 165"><isoentity>Aeacute</isoentity><desc>latin capital letter ae with acute</desc><unientity>01FC</unientity></character>
<character hex="E2 B5" dec="226 181"><isoentity>aeacute</isoentity><desc>latin small letter ae with acute</desc><unientity>01FD</unientity></character>
<character hex="A5" dec="165"><isoentity>AElig</isoentity><desc>latin capital letter ae</desc><unientity>00C6</unientity></character>
<character hex="B5" dec="181"><isoentity>aelig</isoentity><desc>latin small letter ae</desc><unientity>00E6</unientity></character>
<character hex="E5 A5" dec="229 065"><isoentity>Aemacr</isoentity><desc>latin capital letter ae with macron</desc><unientity>01E2</unientity></character>
<character hex="E5 B5" dec="229 097"><isoentity>aemacr</isoentity><desc>latin small letter ae with macron</desc><unientity>01E3</unientity></character>
<character hex="E1 41" dec="225 065"><isoentity>Agrave</isoentity><desc>latin capital letter a with grave</desc><unientity>00C0</unientity></character>
<character hex="E1 61" dec="225 097"><isoentity>agrave</isoentity><desc>latin small letter a with grave</desc><unientity>00E0</unientity></character>
<character hex="E0 41" dec="224 065"><isoentity>Ahooka</isoentity><desc>latin capital letter a with hook above</desc><unientity>1EA2</unientity></character>
<character hex="E0 61" dec="224 097"><isoentity>ahooka</isoentity><desc>latin small letter a with hook above</desc><unientity>1EA3</unientity></character>
<character hex="1B 67 61 1B 73" dec="027 103 097 027 115"><isoentity>alpha</isoentity><desc>greek small letter alpha</desc><unientity>03B1</unientity></character>
<character hex="E5 41" dec="229 065"><isoentity>Amacr</isoentity><desc>latin capital letter a with macron</desc><unientity>0100</unientity></character>
<character hex="E5 61" dec="229 097"><isoentity>amacr</isoentity><desc>latin small letter a with macron</desc><unientity>0101</unientity></character>
<character hex="F1 41" dec="241 065"><isoentity>Aogon</isoentity><desc>latin capital letter a with ogonek</desc><unientity>0104</unientity></character>
<character hex="F1 61" dec="241 097"><isoentity>aogon</isoentity><desc>latin small letter a with ogonek</desc><unientity>0105</unientity></character>
<character hex="E2 EA 41" dec="226 234 065"><isoentity>Aringac</isoentity><desc>latin capital letter a with ring above and acute</desc><unientity>01FA</unientity></character>
<character hex="E2 EA 61" dec="226 234 096"><isoentity>aringac</isoentity><desc>latin small letter a with ring above and acute</desc><unientity>01FB</unientity></character>