From 807b4de28293518671393d0e26505ee0dddbe6a0 Mon Sep 17 00:00:00 2001 From: Daniel Veillard Date: Sun, 26 Sep 2004 14:42:56 +0000 Subject: [PATCH] applied patch from Malcolm Tredinnick fixing errata E20 concerning * valid.c TODO: applied patch from Malcolm Tredinnick fixing errata E20 concerning NMTOKENS and co. validation #153722 * result/VC/AttributeNmtokens test/VC/AttributeNmtokens test/VCM/AttributeNmtokens.xml: also added tests from Malcolm Daniel --- ChangeLog | 8 ++++++ TODO | 49 ---------------------------------- parser.c | 6 ++--- result/VC/AttributeNmtokens | 3 +++ test/VC/AttributeNmtokens | 6 +++++ test/VCM/AttributeNmtokens.xml | 14 ++++++++++ valid.c | 10 ++++--- 7 files changed, 40 insertions(+), 56 deletions(-) create mode 100644 result/VC/AttributeNmtokens create mode 100644 test/VC/AttributeNmtokens create mode 100644 test/VCM/AttributeNmtokens.xml diff --git a/ChangeLog b/ChangeLog index 7909b344..31adaec2 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,6 +1,14 @@ +Sun Sep 26 16:40:24 CEST 2004 Daniel Veillard + + * valid.c TODO: applied patch from Malcolm Tredinnick fixing errata + E20 concerning NMTOKENS and co. validation #153722 + * result/VC/AttributeNmtokens test/VC/AttributeNmtokens + test/VCM/AttributeNmtokens.xml: also added tests from Malcolm + Sun Sep 26 16:24:44 CEST 2004 Daniel Veillard * xstc/xstc.py: applied patch from Malcolm Tredinnick fixing space/tabs + #153713 * xpath.c: fixed a realloc potential problem Fri Sep 24 16:14:12 CEST 2004 Daniel Veillard diff --git a/TODO b/TODO index a53e482c..e348834f 100644 --- a/TODO +++ b/TODO @@ -19,55 +19,6 @@ DOCS: TODO: ===== - -- E20 -[17:21:38] DV, you have an action to Check what your parser does on E20. Have you done this? -[17:22:42] DV, ref: http://www.w3.org/XML/xml-V10-2e-errata#E20 -[17:39:07] paphio:~/XML -> cat tst.xml -[17:39:07] -[17:39:07] -[17:39:07] -[17:39:07] -[17:39:07] ]> -[17:39:07] attr1=" a b " -[17:39:07] attr2=" a b " -[17:39:07] attr3=" a b " -[17:39:07] /> -[17:39:07] paphio:~/XML -> xmllint --valid tst.xml -[17:39:07] -[17:39:07] -[17:39:07] -[17:39:07] -[17:39:07] -[17:39:07] ]> -[17:39:07] -[17:39:07] paphio:~/XML -> -[17:39:16] I think it's okay -[17:40:28] DV, so you're saying that your parser implements E20 correctly, right? -[17:40:48] assuming I understood E20 point correctly, yes -[17:41:15] and that's because I'm unsure taht I pasted the est document and result -[17:41:25] s/ est/ test/ -[17:48:56] does your parser say that document is invalid? -[17:49:03] richard: did I understood it ? -[17:49:11] richard: no it considers it valid -[17:49:16] that document is invalid -[17:49:47] ah , well it's unclear -[17:50:03] the normalized value is a-tab-b, which you are correctly serializing as a b, but it is invalid -[17:50:11] richard: okay -[17:50:23] that should be really easy to fix -[17:50:39] the validity check should require a single space between tokens -[17:51:03] no leading and no trailing either -[17:51:07] right -[17:51:18] which makes sense -[17:52:42] a b is valid, because it turns into a-space-b anyway without any normalization -[17:54:31] okay that's attr2 attr2=" a b " -[17:54:44] * DV tends to still think in hexa -[17:55:59] richard: and attr2="a b" would lead to a validity error too then, if I understand correctly -[17:56:37] attr2 is valid -[17:57:11] the normalized value is a space b - XInclude at the SAX level (libSRVG) - fix the C code prototype to bring back doc/libxml-undocumented.txt to a reasonable level diff --git a/parser.c b/parser.c index 998a97ad..47102708 100644 --- a/parser.c +++ b/parser.c @@ -2342,7 +2342,7 @@ static xmlChar * xmlParseAttValueInternal(xmlParserCtxtPtr ctxt, * * [5] Name ::= (Letter | '_' | ':') (NameChar)* * - * [6] Names ::= Name (S Name)* + * [6] Names ::= Name (#x20 Name)* * * Returns the Name parsed or NULL */ @@ -2467,7 +2467,7 @@ xmlParseNameComplex(xmlParserCtxtPtr ctxt) { * * [5] Name ::= (Letter | '_' | ':') (NameChar)* * - * [6] Names ::= Name (S Name)* + * [6] Names ::= Name (#x20 Name)* * * Returns the Name parsed or NULL. The @str pointer * is updated to the current location in the string. @@ -2547,7 +2547,7 @@ xmlParseStringName(xmlParserCtxtPtr ctxt, const xmlChar** str) { * * [7] Nmtoken ::= (NameChar)+ * - * [8] Nmtokens ::= Nmtoken (S Nmtoken)* + * [8] Nmtokens ::= Nmtoken (#x20 Nmtoken)* * * Returns the Nmtoken parsed or NULL */ diff --git a/result/VC/AttributeNmtokens b/result/VC/AttributeNmtokens new file mode 100644 index 00000000..4c19285b --- /dev/null +++ b/result/VC/AttributeNmtokens @@ -0,0 +1,3 @@ +./test/VC/AttributeNmtokens:6: element test: validity error : Syntax of value for attribute attr1 of test is not valid + + ^ diff --git a/test/VC/AttributeNmtokens b/test/VC/AttributeNmtokens new file mode 100644 index 00000000..8710de48 --- /dev/null +++ b/test/VC/AttributeNmtokens @@ -0,0 +1,6 @@ + + +]> + + diff --git a/test/VCM/AttributeNmtokens.xml b/test/VCM/AttributeNmtokens.xml new file mode 100644 index 00000000..575f8113 --- /dev/null +++ b/test/VCM/AttributeNmtokens.xml @@ -0,0 +1,14 @@ + + + +]> + + + + + + diff --git a/valid.c b/valid.c index f1e50079..6b2d08ec 100644 --- a/valid.c +++ b/valid.c @@ -3306,8 +3306,9 @@ xmlValidateNamesValue(const xmlChar *value) { cur += len; } - while (IS_BLANK(val)) { - while (IS_BLANK(val)) { + /* Should not test IS_BLANK(val) here -- see erratum E20*/ + while (val == 0x20) { + while (val == 0x20) { val = xmlStringCurrentChar(NULL, cur, &len); cur += len; } @@ -3418,8 +3419,9 @@ xmlValidateNmtokensValue(const xmlChar *value) { cur += len; } - while (IS_BLANK(val)) { - while (IS_BLANK(val)) { + /* Should not test IS_BLANK(val) here -- see erratum E20*/ + while (val == 0x20) { + while (val == 0x20) { val = xmlStringCurrentChar(NULL, cur, &len); cur += len; }