diff options
Diffstat (limited to '')
| -rw-r--r-- | ChangeLog | 13 | ||||
| -rw-r--r-- | file.c | 57 | 
2 files changed, 68 insertions, 2 deletions
| @@ -1,3 +1,14 @@ +2002-10-26  Gary Johnson <garyjohn@spk.agilent.com> + +	* [w3m-dev-en 00777] patch to fix w3m-0.3.1 word break problem +	* file.c (is_period_char):  +		0x203A - SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +		(is_beginning_char): +		0x2018 - LEFT SINGLE QUOTATION MARK +		0x2039 - SINGLE LEFT-POINTING ANGLE QUOTATION MARK +		(is_word_char): add several chars ifndef JP_CHARSET +			add ':' and '*' +  2002-10-17  Hiroyuki Ito <hito@crl.go.jp>  	* [w3m-dev 03342] @@ -3941,4 +3952,4 @@  	* release-0-2-1  	* import w3m-0.2.1 -$Id: ChangeLog,v 1.444 2002/10/16 18:13:42 ukai Exp $ +$Id: ChangeLog,v 1.445 2002/10/25 16:00:52 ukai Exp $ @@ -1,4 +1,4 @@ -/* $Id: file.c,v 1.103 2002/10/10 16:59:33 ukai Exp $ */ +/* $Id: file.c,v 1.104 2002/10/25 16:00:54 ukai Exp $ */  #include "fm.h"  #include <sys/types.h>  #include "myctype.h" @@ -2077,6 +2077,9 @@ is_period_char(int ch)      case ']':      case '}':      case '>': +#ifndef JP_CHARSET +    case 0x203A:	/* ">" */ +#endif  	return 1;      default:  	return 0; @@ -2092,6 +2095,10 @@ is_beginning_char(int ch)      case '{':      case '`':      case '<': +#ifndef JP_CHARSET +    case 0x2018:	/* "`" */ +    case 0x2039:	/* "<" */ +#endif  	return 1;      default:  	return 0; @@ -2101,6 +2108,52 @@ is_beginning_char(int ch)  static int  is_word_char(int ch)  { +#ifndef JP_CHARSET +    switch (ch) { +    case 0x0152:	/* "OE"   */ +    case 0x0153:	/* "oe"   */ +	return 1; +    case 0x0178:	/* "Y:"   */ /* ? */ +    case 0x0192:	/* "f"    */ /* ? */ +    case 0x02C6:	/* "^"    */ /* ? */ +	return 0; +    case 0x02DC:	/* "~"    */ +    case 0x03BC:	/* "\xB5" "mu" */ +	return 1; +    case 0x2002:	/* " "    "ensp" */ +    case 0x2003:	/* " "    "emsp" */ +	return 0; +    case 0x2013:	/* "\xAD" "ndash" */ +    case 0x2014:	/* "-"    "mdash" */ +    case 0x2018:	/* "`"    "lsquo" */ +    case 0x2019:	/* "'"    "rsquo" */ +    case 0x201A:	/* "\xB8" "sbquo" */ +    case 0x201C:	/* "\""   "ldquo" */ +    case 0x201D:	/* "\""   "rdquo" */ +    case 0x201E:	/* ",,"   "bdquo" */ +    case 0x2022:	/* "*"    "bull" */ /* ? */ +    case 0x2030:	/* "0/00" "permil" */ +    case 0x2032:	/* "'"    "prime" */ +    case 0x2033:	/* "\""   "Prime" */ +    case 0x2039:	/* "<"    "lsaquo" */ +    case 0x203A:	/* ">"    "rsaquo" */ +    case 0x2044:	/* "/"    "frasl" */ +    case 0x20AC:	/* "=C="  "euro" */ +    case 0x2122:	/* "TM"   "trade" */ +	return 1; +    case 0x2205:	/* "\xF8" "empty" */ /* ? */ +	return 0; +    case 0x2212:	/* "-"    */ +    case 0x223C:	/* "~"    */ +	return 1; +    case 0x2260:	/* "!="   */ /* ? */ +    case 0x2261:	/* "="    */ /* ? */ +    case 0x2264:	/* "<="   */ /* ? */ +    case 0x2265:	/* ">="   */ /* ? */ +	return 0; +    } +#endif +  #ifdef JP_CHARSET      if (is_wckanji(ch) || IS_CNTRL(ch))  	return 0; @@ -2115,10 +2168,12 @@ is_word_char(int ch)      switch (ch) {      case ',':      case '.': +    case ':':      case '\"':			/* " */      case '\'':      case '$':      case '%': +    case '*':      case '+':      case '-':      case '@': | 
