From ae5d181b854d3ccb373b6bc01b4869e44ff4d87a Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sun, 7 Apr 2024 18:37:15 +0200 Subject: Adding upstream version 2.9.0dev.12. Signed-off-by: Daniel Baumann --- test/iso-8859-2a.html | 208 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 208 insertions(+) create mode 100644 test/iso-8859-2a.html (limited to 'test/iso-8859-2a.html') diff --git a/test/iso-8859-2a.html b/test/iso-8859-2a.html new file mode 100644 index 0000000..062b1a5 --- /dev/null +++ b/test/iso-8859-2a.html @@ -0,0 +1,208 @@ + + + + +Martin Ramsch's character table modified and enhanced for iso8859-2 + + + + + + + + + +

iso8859-2 plus table, and cp-1252

+ +
+Description                               Code            Entity name   
+===================================       ============    ==============
+quotation mark                            "  --> "     "   --> "
+ampersand                                 &  --> &     &    --> &
+less-than sign                            &#60;  --> <     &lt;     --> <
+greater-than sign                         &#62;  --> >     &gt;     --> >
+
+Description                          Char Code            Entity name   
+===================================  ==== ============    ==============
+euro sign                                  &128; --> €
+undefined                                  &129; --> 
+single low-9 quotation mark                &130; --> ‚
+latin small letter f with hook             &131; --> ƒ
+double low-9 quotation mark                &132; --> „
+horizontal ellipsis                        &133; --> …
+dagger                                     &134; --> †
+double dagger                              &135; --> ‡
+modifier letter circumflex accent          &136; --> ˆ
+per mille sign                             &137; --> ‰
+latin capital letter s with caron          &138; --> Š
+single left-pointing angle quote mark      &139; --> ‹
+latin capital ligature oe                  &140; --> Œ
+undefined                                  &141; --> 
+latin capital letter z with caron          &142; --> Ž
+undefined                                  &143; --> 
+
+undefined                                  &144; --> 
+left single quotation mark                 &145; --> ‘
+right single quotation mark                &146; --> ’
+left double quotation mark                 &147; --> “
+right double quotation mark                &148; --> ”
+bullet                                     &149; --> •
+en dash                                    &150; --> –
+em dash                                    &151; --> —
+small tilde                                &152; --> ˜
+trade mark sign                            &153; --> ™
+latin small letter s with caron            &154; --> š
+single right-pointing angle quote mark     &155; --> ›
+latin small ligature oe                    &156; --> œ
+undefined                                  &157; --> 
+latin small letter z with caron            &158; --> ž
+latin capital letter y with diaeresis      &159; --> Ÿ
+
+non-breaking space                       &#160; -->      &nbsp;   -->  
+capital A, ogonek                        &#260; --> Ą    &Aogon;  --> Ą
+breve                               {}  {&#728;}-->{˘}  {&breve;} -->{˘}
+capital L, stroke                        &#321; --> Ł    &Lstrok; --> Ł
+general currency sign                    &#164; --> ¤    &curren; --> ¤
+capital L, caron                         &#317; --> Ľ    &Lcaron; --> Ľ
+capital S, acute accent                  &#346; --> Ś    &Sacute; --> Ś
+section sign                             &#167; --> §    &sect;   --> §
+umlaut (dieresis)                        &#168; --> ¨    &uml;    --> ¨
+                                                          &die;    --> ¨
+capital S, caron                         &#352; --> Š    &Scaron; --> Š
+capital S, cedilla                       &#350; --> Ş    &Scedil; --> Ş
+capital T, caron                         &#356; --> Ť    &Tcaron; --> Ť
+capital Z, acute accent                  &#377; --> Ź    &Zacute; --> Ź
+soft hyphen                         []  [&#173;]-->[­]  [&shy;]   -->[­]
+capital Z, caron                         &#381; --> Ž    &Zcaron; --> Ž
+capital Z, dot above                     &#379; --> Ż    &Zdot;   --> Ż
+degree sign                              &#176; --> °    &deg;    --> °
+small a, ogonek                          &#261; --> ą    &aogon;  --> ą
+ogonek                              {}  {&#731;}-->{˛}  {&ogon;}  -->{˛}
+small l, stroke                          &#322; --> ł    &lstrok; --> ł
+acute accent                             &#180; --> ´    &acute;  --> ´
+small l, caron                           &#318; --> ľ    &lcaron; --> ľ
+small s, acute accent                    &#347; --> ś    &sacute; --> ś
+caron                               {}  {&#711;}-->{ˇ}  {&caron;} -->{ˇ}
+cedilla                                  &#184; --> ¸    &cedil;  --> ¸
+small s, caron                           &#353; --> š    &scaron; --> š
+small s, cedilla                         &#351; --> ş    &scedil; --> ş
+small t, caron                           &#357; --> ť    &tcaron; --> ť
+small z, acute accent                    &#378; --> ź    &zacute; --> ź
+double acute accent                 {}  {&#733;}-->{˝}  {&dblac;} -->{˝}
+small z, caron                           &#382; --> ž    &zcaron; --> ž
+small z, dot above                       &#380; --> ż    &zdot;   --> ż  
+capital R, acute accent                  &#340; --> Ŕ    &Racute; --> Ŕ
+capital A, acute accent                  &#193; --> Á    &Aacute; --> Á
+capital A, circumflex accent             &#194; --> Â    &Acirc;  --> Â
+capital A, breve                         &#258; --> Ă    &Abreve; --> Ă
+capital A, dieresis or umlaut mark       &#196; --> Ä    &Auml;   --> Ä
+capital L, acute accent                  &#313; --> Ĺ    &Lacute; --> Ĺ
+capital C, acute accent                  &#262; --> Ć    &Cacute; --> Ć
+capital C, cedilla                       &#199; --> Ç    &Ccedil; --> Ç
+capital C, caron                         &#268; --> Č    &Ccaron; --> Č
+capital E, acute accent                  &#201; --> É    &Eacute; --> É
+capital E, ogonek                        &#280; --> Ę    &Eogon;  --> Ę
+capital E, dieresis or umlaut mark       &#203; --> Ë    &Euml;   --> Ë
+capital E, caron                         &#282; --> Ě    &Ecaron; --> Ě
+capital I, acute accent                  &#205; --> Í    &Iacute; --> Í
+capital I, circumflex accent             &#206; --> Î    &Icirc;  --> Î
+capital D, caron                         &#270; --> Ď    &Dcaron; --> Ď
+capital D, stroke                        &#272; --> Đ    &Dstrok; --> Đ
+capital Eth, Icelandic               N/A  &#208; --> Ð    &ETH;    --> Ð
+capital N, acute accent                  &#323; --> Ń    &Nacute; --> Ń
+capital N, caron                         &#327; --> Ň    &Ncaron; --> Ň
+capital O, acute accent                  &#211; --> Ó    &Oacute; --> Ó
+capital O, circumflex accent             &#212; --> Ô    &Ocirc;  --> Ô
+capital O, double acute accent           &#368; --> Ű    &Odblac; --> Ő
+capital O, dieresis or umlaut mark       &#214; --> Ö    &Ouml;   --> Ö
+multiply sign                            &#215; --> ×    &times;  --> ×
+capital R, caron                         &#344; --> Ř    &Rcaron; --> Ř
+capital U, ring                          &#366; --> Ů    &Uring;  --> Ů
+capital U, acute accent                  &#218; --> Ú    &Uacute; --> Ú
+capital U, double acute accent           &#368; --> Ű    &Udblac; --> Ű
+capital U, dieresis or umlaut mark       &#220; --> Ü    &Uuml;   --> Ü
+capital Y, acute accent                  &#221; --> Ý    &Yacute; --> Ý
+capital T, cedilla                       &#354; --> Ţ    &Tcedil; --> Ţ
+small sharp s, German (sz ligature)      &#223; --> ß    &szlig;  --> ß
+small r, acute accent                    &#341; --> ŕ    &racute; --> ŕ
+small a, acute accent                    &#225; --> á    &aacute; --> á
+small a, circumflex accent               &#226; --> â    &acirc;  --> â
+small a, breve                           &#259; --> ă    &abreve; --> ă
+small a, dieresis or umlaut mark         &#228; --> ä    &auml;   --> ä
+small l, acute accent                    &#314; --> ĺ    &lacute; --> ĺ
+small c, acute accent                    &#263; --> ć    &cacute; --> ć
+small c, cedilla                         &#231; --> ç    &ccedil; --> ç
+small c, caron                           &#269; --> č    &ccaron; --> č
+small e, acute accent                    &#233; --> é    &eacute; --> é
+small e, ogonek                          &#281; --> ę    &eogon;  --> ę
+small e, dieresis or umlaut mark         &#235; --> ë    &euml;   --> ë
+small e, caron                           &#283; --> ě    &ecaron; --> ě
+small i, acute accent                    &#237; --> í    &iacute; --> í
+small i, circumflex accent               &#238; --> î    &icirc;  --> î
+small d, caron                           &#271; --> ď    &dcaron; --> ď
+small d, stroke                          &#273; --> đ    &dstrok; --> đ
+small eth, Icelandic                 N/A  &#240; --> ð    &eth;    --> ð
+small n, acute accent                    &#324; --> ń    &nacute; --> ń
+small n, caron                           &#328; --> ň    &ncaron; --> ň
+small o, acute accent                    &#243; --> ó    &oacute; --> ó
+small o, circumflex accent               &#244; --> ô    &ocirc;  --> ô
+small o, double acute accent             &#369; --> ű    &odblac; --> ő
+small o, dieresis or umlaut mark         &#246; --> ö    &ouml;   --> ö
+division sign                            &#247; --> ÷    &divide; --> ÷
+small r, caron                           &#345; --> ř    &rcaron; --> ř
+small u, ring                            &#367; --> ů    &uring;  --> ů
+small u, acute accent                    &#250; --> ú    &uacute; --> ú
+small u, double acute accent             &#369; --> ű    &udblac; --> ű
+small u, dieresis or umlaut mark         &#252; --> ü    &uuml;   --> ü
+small y, acute accent                    &#253; --> ý    &yacute; --> ý
+small t, cedilla                         &#355; --> ţ    &tcedil; --> ţ
+dot above                           {}  {&#729;}-->{˙}  {&dot;}   -->{˙}
+
+Some other characters of interest    Char Code            Entity name   
+===================================  ==== ============    ==============
+capital AE diphthong (ligature)      N/A  &#198; --> Æ    &AElig;  --> Æ
+small ae diphthong (ligature)        N/A  &#230; --> æ    &aelig;  --> æ
+capital OE ligature                  N/A {&#338;}-->{Œ}  {&OElig;} -->{Œ}
+small oe ligature                    N/A {&#339;}-->{œ}  {&oelig;} -->{œ}
+copyright                            N/A  &#169; --> ©    &copy;   --> ©
+registered trademark                 N/A  &#174; --> ®    &reg;    --> ®
+trademark sign                       N/A  &#8482;--> ™   &trade;  --> ™
+em space                             N/A [&#8195;]->[ ] [&emsp;]  -->[ ]
+en space                             N/A [&#8194;]->[ ] [&ensp;]  -->[ ]
+1/3-em space                         N/A [&#8196;]->[ ] [&emsp13;] -->[ ]
+1/4-em space                         N/A [&#8197;]->[ ] [&emsp14;] -->[ ]
+thin space                           N/A [&#8201;]->[ ] [&thinsp;]-->[ ]
+hair space                           N/A [&#8202;]->[ ] [&hairsp;]-->[ ]
+em dash                              N/A [&#8212;]->[—] [&mdash;] -->[—]
+en dash                              N/A [&#8211;]->[–] [&ndash;] -->[–]
+
+
+ +
+

+Characters not found in ISO-8859-2 have "N/A" in the Char column. +Some characters for which I could not find entity names in either +RFC 2070 +or the +ISOlat1, ISOlat2, ISOnum, ISOpub and ISOtech +sets (the ones included by Peter Flynn's +HTML Pro DTD) +are shown enclosed in {braces}. +

+

+There also is a variation of this table which tests +ISO-8859-2 characters and entities in ALT attributes. +

+

+See Martin Ramsch's original +ISO-8859-1 Table +for related info and links, and for some notes on entity names. +This file is mostly just an adaptation of his table +to the ISO-8859-2 character set. +

+
+ +
kweide@tezcat.com 1997-03-09
+ + + -- cgit v1.2.3