diff options
author | Andreas Rottmann <a.rottmann@gmx.at> | 2010-05-27 18:23:15 +0200 |
---|---|---|
committer | Andreas Rottmann <a.rottmann@gmx.at> | 2010-05-27 18:23:15 +0200 |
commit | 3e0814cd9862b89c7a39672672937477bd87ddfb (patch) | |
tree | 159134a624e51509f40ed8823249f09a70d1dda3 /lib/unilbrk | |
parent | 3bebb94360f1c2333feb8d504a9fa4f96984d8b7 (diff) |
Imported Upstream version 0.9.3upstream/0.9.3
Diffstat (limited to 'lib/unilbrk')
-rw-r--r-- | lib/unilbrk/lbrkprop1.h | 2 | ||||
-rw-r--r-- | lib/unilbrk/lbrkprop2.h | 2 | ||||
-rw-r--r-- | lib/unilbrk/lbrktables.c | 6 | ||||
-rw-r--r-- | lib/unilbrk/lbrktables.h | 20 | ||||
-rw-r--r-- | lib/unilbrk/u16-possible-linebreaks.c | 216 | ||||
-rw-r--r-- | lib/unilbrk/u16-width-linebreaks.c | 84 | ||||
-rw-r--r-- | lib/unilbrk/u32-possible-linebreaks.c | 216 | ||||
-rw-r--r-- | lib/unilbrk/u32-width-linebreaks.c | 84 | ||||
-rw-r--r-- | lib/unilbrk/u8-possible-linebreaks.c | 290 | ||||
-rw-r--r-- | lib/unilbrk/u8-width-linebreaks.c | 152 | ||||
-rw-r--r-- | lib/unilbrk/ulc-common.c | 4 | ||||
-rw-r--r-- | lib/unilbrk/ulc-common.h | 2 | ||||
-rw-r--r-- | lib/unilbrk/ulc-possible-linebreaks.c | 196 | ||||
-rw-r--r-- | lib/unilbrk/ulc-width-linebreaks.c | 232 |
14 files changed, 753 insertions, 753 deletions
diff --git a/lib/unilbrk/lbrkprop1.h b/lib/unilbrk/lbrkprop1.h index 66fd5849..ba6e1b86 100644 --- a/lib/unilbrk/lbrkprop1.h +++ b/lib/unilbrk/lbrkprop1.h @@ -2,7 +2,7 @@ /* Line breaking properties of Unicode characters. */ /* Generated automatically by gen-lbrk for Unicode 5.1.0. */ -/* Copyright (C) 2000-2002, 2004, 2008 Free Software Foundation, Inc. +/* Copyright (C) 2000-2002, 2004, 2008-2010 Free Software Foundation, Inc. This program is free software: you can redistribute it and/or modify it under the terms of the GNU Lesser General Public License as published by diff --git a/lib/unilbrk/lbrkprop2.h b/lib/unilbrk/lbrkprop2.h index a71b4d9e..45b93b1b 100644 --- a/lib/unilbrk/lbrkprop2.h +++ b/lib/unilbrk/lbrkprop2.h @@ -2,7 +2,7 @@ /* Line breaking properties of Unicode characters. */ /* Generated automatically by gen-lbrk for Unicode 5.1.0. */ -/* Copyright (C) 2000-2002, 2004, 2008 Free Software Foundation, Inc. +/* Copyright (C) 2000-2002, 2004, 2008-2010 Free Software Foundation, Inc. This program is free software: you can redistribute it and/or modify it under the terms of the GNU Lesser General Public License as published by diff --git a/lib/unilbrk/lbrktables.c b/lib/unilbrk/lbrktables.c index ae3ebf4f..fbc89311 100644 --- a/lib/unilbrk/lbrktables.c +++ b/lib/unilbrk/lbrktables.c @@ -1,5 +1,5 @@ /* Line breaking auxiliary tables. - Copyright (C) 2001-2003, 2006-2009 Free Software Foundation, Inc. + Copyright (C) 2001-2003, 2006-2010 Free Software Foundation, Inc. Written by Bruno Haible <bruno@clisp.org>, 2001. This program is free software: you can redistribute it and/or modify it @@ -25,8 +25,8 @@ const unsigned char unilbrk_table[24][24] = { - /* after */ - /* WJ GL B2 BA BB HY CL EX IN NS OP QU IS NU PO PR SY AL H2 H3 ID JL JV JT */ + /* after */ + /* WJ GL B2 BA BB HY CL EX IN NS OP QU IS NU PO PR SY AL H2 H3 ID JL JV JT */ /* WJ */ { P, I, I, I, I, I, P, P, I, I, I, I, P, I, I, I, P, I, I, I, I, I, I, I, }, /* GL */ { P, I, I, I, I, I, P, P, I, I, I, I, P, I, I, I, P, I, I, I, I, I, I, I, }, /* B2 */ { P, I, P, I, D, I, P, P, D, I, D, I, P, D, D, D, P, D, D, D, D, D, D, D, }, diff --git a/lib/unilbrk/lbrktables.h b/lib/unilbrk/lbrktables.h index 33b525be..e86c49ff 100644 --- a/lib/unilbrk/lbrktables.h +++ b/lib/unilbrk/lbrktables.h @@ -1,5 +1,5 @@ /* Line breaking auxiliary tables. - Copyright (C) 2001-2003, 2006-2008 Free Software Foundation, Inc. + Copyright (C) 2001-2003, 2006-2010 Free Software Foundation, Inc. Written by Bruno Haible <bruno@clisp.org>, 2001. This program is free software: you can redistribute it and/or modify it @@ -70,15 +70,15 @@ unilbrkprop_lookup (ucs4_t uc) { int lookup1 = unilbrkprop.level1[index1]; if (lookup1 >= 0) - { - unsigned int index2 = (uc >> lbrkprop_header_2) & lbrkprop_header_3; - int lookup2 = unilbrkprop.level2[lookup1 + index2]; - if (lookup2 >= 0) - { - unsigned int index3 = uc & lbrkprop_header_4; - return unilbrkprop.level3[lookup2 + index3]; - } - } + { + unsigned int index2 = (uc >> lbrkprop_header_2) & lbrkprop_header_3; + int lookup2 = unilbrkprop.level2[lookup1 + index2]; + if (lookup2 >= 0) + { + unsigned int index3 = uc & lbrkprop_header_4; + return unilbrkprop.level3[lookup2 + index3]; + } + } } return LBP_XX; } diff --git a/lib/unilbrk/u16-possible-linebreaks.c b/lib/unilbrk/u16-possible-linebreaks.c index f5b69921..25b9851a 100644 --- a/lib/unilbrk/u16-possible-linebreaks.c +++ b/lib/unilbrk/u16-possible-linebreaks.c @@ -1,5 +1,5 @@ /* Line breaking of UTF-16 strings. - Copyright (C) 2001-2003, 2006-2009 Free Software Foundation, Inc. + Copyright (C) 2001-2003, 2006-2010 Free Software Foundation, Inc. Written by Bruno Haible <bruno@clisp.org>, 2001. This program is free software: you can redistribute it and/or modify it @@ -46,117 +46,117 @@ u16_possible_linebreaks (const uint16_t *s, size_t n, const char *encoding, char int prop = unilbrkprop_lookup (uc); if (prop == LBP_BK) - { - /* Mandatory break. */ - *p = UC_BREAK_MANDATORY; - last_prop = LBP_BK; - seen_space = NULL; - seen_space2 = NULL; - } + { + /* Mandatory break. */ + *p = UC_BREAK_MANDATORY; + last_prop = LBP_BK; + seen_space = NULL; + seen_space2 = NULL; + } else - { - char *q; + { + char *q; - /* Resolve property values whose behaviour is not fixed. */ - switch (prop) - { - case LBP_AI: - /* Resolve ambiguous. */ - prop = LBP_AI_REPLACEMENT; - break; - case LBP_CB: - /* This is arbitrary. */ - prop = LBP_ID; - break; - case LBP_SA: - /* We don't handle complex scripts yet. - Treat LBP_SA like LBP_XX. */ - case LBP_XX: - /* This is arbitrary. */ - prop = LBP_AL; - break; - } + /* Resolve property values whose behaviour is not fixed. */ + switch (prop) + { + case LBP_AI: + /* Resolve ambiguous. */ + prop = LBP_AI_REPLACEMENT; + break; + case LBP_CB: + /* This is arbitrary. */ + prop = LBP_ID; + break; + case LBP_SA: + /* We don't handle complex scripts yet. + Treat LBP_SA like LBP_XX. */ + case LBP_XX: + /* This is arbitrary. */ + prop = LBP_AL; + break; + } - /* Deal with spaces and combining characters. */ - q = p; - if (prop == LBP_SP) - { - /* Don't break just before a space. */ - *p = UC_BREAK_PROHIBITED; - seen_space2 = seen_space; - seen_space = p; - } - else if (prop == LBP_ZW) - { - /* Don't break just before a zero-width space. */ - *p = UC_BREAK_PROHIBITED; - last_prop = LBP_ZW; - seen_space = NULL; - seen_space2 = NULL; - } - else if (prop == LBP_CM) - { - /* Don't break just before a combining character, except immediately after a - zero-width space. */ - if (last_prop == LBP_ZW) - { - /* Break after zero-width space. */ - *p = UC_BREAK_POSSIBLE; - /* A combining character turns a preceding space into LBP_ID. */ - last_prop = LBP_ID; - } - else - { - *p = UC_BREAK_PROHIBITED; - /* A combining character turns a preceding space into LBP_ID. */ - if (seen_space != NULL) - { - q = seen_space; - seen_space = seen_space2; - prop = LBP_ID; - goto lookup_via_table; - } - } - } - else - { - lookup_via_table: - /* prop must be usable as an index for table 7.3 of UTR #14. */ - if (!(prop >= 0 && prop < sizeof (unilbrk_table) / sizeof (unilbrk_table[0]))) - abort (); + /* Deal with spaces and combining characters. */ + q = p; + if (prop == LBP_SP) + { + /* Don't break just before a space. */ + *p = UC_BREAK_PROHIBITED; + seen_space2 = seen_space; + seen_space = p; + } + else if (prop == LBP_ZW) + { + /* Don't break just before a zero-width space. */ + *p = UC_BREAK_PROHIBITED; + last_prop = LBP_ZW; + seen_space = NULL; + seen_space2 = NULL; + } + else if (prop == LBP_CM) + { + /* Don't break just before a combining character, except immediately after a + zero-width space. */ + if (last_prop == LBP_ZW) + { + /* Break after zero-width space. */ + *p = UC_BREAK_POSSIBLE; + /* A combining character turns a preceding space into LBP_ID. */ + last_prop = LBP_ID; + } + else + { + *p = UC_BREAK_PROHIBITED; + /* A combining character turns a preceding space into LBP_ID. */ + if (seen_space != NULL) + { + q = seen_space; + seen_space = seen_space2; + prop = LBP_ID; + goto lookup_via_table; + } + } + } + else + { + lookup_via_table: + /* prop must be usable as an index for table 7.3 of UTR #14. */ + if (!(prop >= 0 && prop < sizeof (unilbrk_table) / sizeof (unilbrk_table[0]))) + abort (); - if (last_prop == LBP_BK) - { - /* Don't break at the beginning of a line. */ - *q = UC_BREAK_PROHIBITED; - } - else if (last_prop == LBP_ZW) - { - /* Break after zero-width space. */ - *q = UC_BREAK_POSSIBLE; - } - else - { - switch (unilbrk_table [last_prop] [prop]) - { - case D: - *q = UC_BREAK_POSSIBLE; - break; - case I: - *q = (seen_space != NULL ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED); - break; - case P: - *q = UC_BREAK_PROHIBITED; - break; - default: - abort (); - } - } - last_prop = prop; - seen_space = NULL; - seen_space2 = NULL; - } - } + if (last_prop == LBP_BK) + { + /* Don't break at the beginning of a line. */ + *q = UC_BREAK_PROHIBITED; + } + else if (last_prop == LBP_ZW) + { + /* Break after zero-width space. */ + *q = UC_BREAK_POSSIBLE; + } + else + { + switch (unilbrk_table [last_prop] [prop]) + { + case D: + *q = UC_BREAK_POSSIBLE; + break; + case I: + *q = (seen_space != NULL ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED); + break; + case P: + *q = UC_BREAK_PROHIBITED; + break; + default: + abort (); + } + } + last_prop = prop; + seen_space = NULL; + seen_space2 = NULL; + } + } s += count; p += count; diff --git a/lib/unilbrk/u16-width-linebreaks.c b/lib/unilbrk/u16-width-linebreaks.c index 64445590..152178e5 100644 --- a/lib/unilbrk/u16-width-linebreaks.c +++ b/lib/unilbrk/u16-width-linebreaks.c @@ -1,5 +1,5 @@ /* Line breaking of UTF-16 strings. - Copyright (C) 2001-2003, 2006-2008 Free Software Foundation, Inc. + Copyright (C) 2001-2003, 2006-2010 Free Software Foundation, Inc. Written by Bruno Haible <bruno@clisp.org>, 2001. This program is free software: you can redistribute it and/or modify it @@ -25,9 +25,9 @@ int u16_width_linebreaks (const uint16_t *s, size_t n, - int width, int start_column, int at_end_columns, - const char *o, const char *encoding, - char *p) + int width, int start_column, int at_end_columns, + const char *o, const char *encoding, + char *p) { const uint16_t *s_end; char *last_p; @@ -47,53 +47,53 @@ u16_width_linebreaks (const uint16_t *s, size_t n, /* Respect the override. */ if (o != NULL && *o != UC_BREAK_UNDEFINED) - *p = *o; + *p = *o; if (*p == UC_BREAK_POSSIBLE || *p == UC_BREAK_MANDATORY) - { - /* An atomic piece of text ends here. */ - if (last_p != NULL && last_column + piece_width > width) - { - /* Insert a line break. */ - *last_p = UC_BREAK_POSSIBLE; - last_column = 0; - } - } + { + /* An atomic piece of text ends here. */ + if (last_p != NULL && last_column + piece_width > width) + { + /* Insert a line break. */ + *last_p = UC_BREAK_POSSIBLE; + last_column = 0; + } + } if (*p == UC_BREAK_MANDATORY) - { - /* uc is a line break character. */ - /* Start a new piece at column 0. */ - last_p = NULL; - last_column = 0; - piece_width = 0; - } + { + /* uc is a line break character. */ + /* Start a new piece at column 0. */ + last_p = NULL; + last_column = 0; + piece_width = 0; + } else - { - /* uc is not a line break character. */ - int w; - - if (*p == UC_BREAK_POSSIBLE) - { - /* Start a new piece. */ - last_p = p; - last_column += piece_width; - piece_width = 0; - /* No line break for the moment, may be turned into - UC_BREAK_POSSIBLE later, via last_p. */ - } - - *p = UC_BREAK_PROHIBITED; - - w = uc_width (uc, encoding); - if (w >= 0) /* ignore control characters in the string */ - piece_width += w; - } + { + /* uc is not a line break character. */ + int w; + + if (*p == UC_BREAK_POSSIBLE) + { + /* Start a new piece. */ + last_p = p; + last_column += piece_width; + piece_width = 0; + /* No line break for the moment, may be turned into + UC_BREAK_POSSIBLE later, via last_p. */ + } + + *p = UC_BREAK_PROHIBITED; + + w = uc_width (uc, encoding); + if (w >= 0) /* ignore control characters in the string */ + piece_width += w; + } s += count; p += count; if (o != NULL) - o += count; + o += count; } /* The last atomic piece of text ends here. */ diff --git a/lib/unilbrk/u32-possible-linebreaks.c b/lib/unilbrk/u32-possible-linebreaks.c index c843e12b..c375a0c7 100644 --- a/lib/unilbrk/u32-possible-linebreaks.c +++ b/lib/unilbrk/u32-possible-linebreaks.c @@ -1,5 +1,5 @@ /* Line breaking of UTF-32 strings. - Copyright (C) 2001-2003, 2006-2009 Free Software Foundation, Inc. + Copyright (C) 2001-2003, 2006-2010 Free Software Foundation, Inc. Written by Bruno Haible <bruno@clisp.org>, 2001. This program is free software: you can redistribute it and/or modify it @@ -40,117 +40,117 @@ u32_possible_linebreaks (const uint32_t *s, size_t n, const char *encoding, char int prop = unilbrkprop_lookup (uc); if (prop == LBP_BK) - { - /* Mandatory break. */ - *p = UC_BREAK_MANDATORY; - last_prop = LBP_BK; - seen_space = NULL; - seen_space2 = NULL; - } + { + /* Mandatory break. */ + *p = UC_BREAK_MANDATORY; + last_prop = LBP_BK; + seen_space = NULL; + seen_space2 = NULL; + } else - { - char *q; + { + char *q; - /* Resolve property values whose behaviour is not fixed. */ - switch (prop) - { - case LBP_AI: - /* Resolve ambiguous. */ - prop = LBP_AI_REPLACEMENT; - break; - case LBP_CB: - /* This is arbitrary. */ - prop = LBP_ID; - break; - case LBP_SA: - /* We don't handle complex scripts yet. - Treat LBP_SA like LBP_XX. */ - case LBP_XX: - /* This is arbitrary. */ - prop = LBP_AL; - break; - } + /* Resolve property values whose behaviour is not fixed. */ + switch (prop) + { + case LBP_AI: + /* Resolve ambiguous. */ + prop = LBP_AI_REPLACEMENT; + break; + case LBP_CB: + /* This is arbitrary. */ + prop = LBP_ID; + break; + case LBP_SA: + /* We don't handle complex scripts yet. + Treat LBP_SA like LBP_XX. */ + case LBP_XX: + /* This is arbitrary. */ + prop = LBP_AL; + break; + } - /* Deal with spaces and combining characters. */ - q = p; - if (prop == LBP_SP) - { - /* Don't break just before a space. */ - *p = UC_BREAK_PROHIBITED; - seen_space2 = seen_space; - seen_space = p; - } - else if (prop == LBP_ZW) - { - /* Don't break just before a zero-width space. */ - *p = UC_BREAK_PROHIBITED; - last_prop = LBP_ZW; - seen_space = NULL; - seen_space2 = NULL; - } - else if (prop == LBP_CM) - { - /* Don't break just before a combining character, except immediately after a - zero-width space. */ - if (last_prop == LBP_ZW) - { - /* Break after zero-width space. */ - *p = UC_BREAK_POSSIBLE; - /* A combining character turns a preceding space into LBP_ID. */ - last_prop = LBP_ID; - } - else - { - *p = UC_BREAK_PROHIBITED; - /* A combining character turns a preceding space into LBP_ID. */ - if (seen_space != NULL) - { - q = seen_space; - seen_space = seen_space2; - prop = LBP_ID; - goto lookup_via_table; - } - } - } - else - { - lookup_via_table: - /* prop must be usable as an index for table 7.3 of UTR #14. */ - if (!(prop >= 0 && prop < sizeof (unilbrk_table) / sizeof (unilbrk_table[0]))) - abort (); + /* Deal with spaces and combining characters. */ + q = p; + if (prop == LBP_SP) + { + /* Don't break just before a space. */ + *p = UC_BREAK_PROHIBITED; + seen_space2 = seen_space; + seen_space = p; + } + else if (prop == LBP_ZW) + { + /* Don't break just before a zero-width space. */ + *p = UC_BREAK_PROHIBITED; + last_prop = LBP_ZW; + seen_space = NULL; + seen_space2 = NULL; + } + else if (prop == LBP_CM) + { + /* Don't break just before a combining character, except immediately after a + zero-width space. */ + if (last_prop == LBP_ZW) + { + /* Break after zero-width space. */ + *p = UC_BREAK_POSSIBLE; + /* A combining character turns a preceding space into LBP_ID. */ + last_prop = LBP_ID; + } + else + { + *p = UC_BREAK_PROHIBITED; + /* A combining character turns a preceding space into LBP_ID. */ + if (seen_space != NULL) + { + q = seen_space; + seen_space = seen_space2; + prop = LBP_ID; + goto lookup_via_table; + } + } + } + else + { + lookup_via_table: + /* prop must be usable as an index for table 7.3 of UTR #14. */ + if (!(prop >= 0 && prop < sizeof (unilbrk_table) / sizeof (unilbrk_table[0]))) + abort (); - if (last_prop == LBP_BK) - { - /* Don't break at the beginning of a line. */ - *q = UC_BREAK_PROHIBITED; - } - else if (last_prop == LBP_ZW) - { - /* Break after zero-width space. */ - *q = UC_BREAK_POSSIBLE; - } - else - { - switch (unilbrk_table [last_prop] [prop]) - { - case D: - *q = UC_BREAK_POSSIBLE; - break; - case I: - *q = (seen_space != NULL ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED); - break; - case P: - *q = UC_BREAK_PROHIBITED; - break; - default: - abort (); - } - } - last_prop = prop; - seen_space = NULL; - seen_space2 = NULL; - } - } + if (last_prop == LBP_BK) + { + /* Don't break at the beginning of a line. */ + *q = UC_BREAK_PROHIBITED; + } + else if (last_prop == LBP_ZW) + { + /* Break after zero-width space. */ + *q = UC_BREAK_POSSIBLE; + } + else + { + switch (unilbrk_table [last_prop] [prop]) + { + case D: + *q = UC_BREAK_POSSIBLE; + break; + case I: + *q = (seen_space != NULL ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED); + break; + case P: + *q = UC_BREAK_PROHIBITED; + break; + default: + abort (); + } + } + last_prop = prop; + seen_space = NULL; + seen_space2 = NULL; + } + } s++; p++; diff --git a/lib/unilbrk/u32-width-linebreaks.c b/lib/unilbrk/u32-width-linebreaks.c index 2d362560..c5803dbf 100644 --- a/lib/unilbrk/u32-width-linebreaks.c +++ b/lib/unilbrk/u32-width-linebreaks.c @@ -1,5 +1,5 @@ /* Line breaking of UTF-32 strings. - Copyright (C) 2001-2003, 2006-2008 Free Software Foundation, Inc. + Copyright (C) 2001-2003, 2006-2010 Free Software Foundation, Inc. Written by Bruno Haible <bruno@clisp.org>, 2001. This program is free software: you can redistribute it and/or modify it @@ -24,9 +24,9 @@ int u32_width_linebreaks (const uint32_t *s, size_t n, - int width, int start_column, int at_end_columns, - const char *o, const char *encoding, - char *p) + int width, int start_column, int at_end_columns, + const char *o, const char *encoding, + char *p) { const uint32_t *s_end; char *last_p; @@ -45,53 +45,53 @@ u32_width_linebreaks (const uint32_t *s, size_t n, /* Respect the override. */ if (o != NULL && *o != UC_BREAK_UNDEFINED) - *p = *o; + *p = *o; if (*p == UC_BREAK_POSSIBLE || *p == UC_BREAK_MANDATORY) - { - /* An atomic piece of text ends here. */ - if (last_p != NULL && last_column + piece_width > width) - { - /* Insert a line break. */ - *last_p = UC_BREAK_POSSIBLE; - last_column = 0; - } - } + { + /* An atomic piece of text ends here. */ + if (last_p != NULL && last_column + piece_width > width) + { + /* Insert a line break. */ + *last_p = UC_BREAK_POSSIBLE; + last_column = 0; + } + } if (*p == UC_BREAK_MANDATORY) - { - /* uc is a line break character. */ - /* Start a new piece at column 0. */ - last_p = NULL; - last_column = 0; - piece_width = 0; - } + { + /* uc is a line break character. */ + /* Start a new piece at column 0. */ + last_p = NULL; + last_column = 0; + piece_width = 0; + } else - { - /* uc is not a line break character. */ - int w; - - if (*p == UC_BREAK_POSSIBLE) - { - /* Start a new piece. */ - last_p = p; - last_column += piece_width; - piece_width = 0; - /* No line break for the moment, may be turned into - UC_BREAK_POSSIBLE later, via last_p. */ - } - - *p = UC_BREAK_PROHIBITED; - - w = uc_width (uc, encoding); - if (w >= 0) /* ignore control characters in the string */ - piece_width += w; - } + { + /* uc is not a line break character. */ + int w; + + if (*p == UC_BREAK_POSSIBLE) + { + /* Start a new piece. */ + last_p = p; + last_column += piece_width; + piece_width = 0; + /* No line break for the moment, may be turned into + UC_BREAK_POSSIBLE later, via last_p. */ + } + + *p = UC_BREAK_PROHIBITED; + + w = uc_width (uc, encoding); + if (w >= 0) /* ignore control characters in the string */ + piece_width += w; + } s++; p++; if (o != NULL) - o++; + o++; } /* The last atomic piece of text ends here. */ diff --git a/lib/unilbrk/u8-possible-linebreaks.c b/lib/unilbrk/u8-possible-linebreaks.c index 94e14f40..d65335ea 100644 --- a/lib/unilbrk/u8-possible-linebreaks.c +++ b/lib/unilbrk/u8-possible-linebreaks.c @@ -1,5 +1,5 @@ /* Line breaking of UTF-8 strings. - Copyright (C) 2001-2003, 2006-2009 Free Software Foundation, Inc. + Copyright (C) 2001-2003, 2006-2010 Free Software Foundation, Inc. Written by Bruno Haible <bruno@clisp.org>, 2001. This program is free software: you can redistribute it and/or modify it @@ -46,117 +46,117 @@ u8_possible_linebreaks (const uint8_t *s, size_t n, const char *encoding, char * int prop = unilbrkprop_lookup (uc); if (prop == LBP_BK) - { - /* Mandatory break. */ - *p = UC_BREAK_MANDATORY; - last_prop = LBP_BK; - seen_space = NULL; - seen_space2 = NULL; - } + { + /* Mandatory break. */ + *p = UC_BREAK_MANDATORY; + last_prop = LBP_BK; + seen_space = NULL; + seen_space2 = NULL; + } else - { - char *q; + { + char *q; - /* Resolve property values whose behaviour is not fixed. */ - switch (prop) - { - case LBP_AI: - /* Resolve ambiguous. */ - prop = LBP_AI_REPLACEMENT; - break; - case LBP_CB: - /* This is arbitrary. */ - prop = LBP_ID; - break; - case LBP_SA: - /* We don't handle complex scripts yet. - Treat LBP_SA like LBP_XX. */ - case LBP_XX: - /* This is arbitrary. */ - prop = LBP_AL; - break; - } + /* Resolve property values whose behaviour is not fixed. */ + switch (prop) + { + case LBP_AI: + /* Resolve ambiguous. */ + prop = LBP_AI_REPLACEMENT; + break; + case LBP_CB: + /* This is arbitrary. */ + prop = LBP_ID; + break; + case LBP_SA: + /* We don't handle complex scripts yet. + Treat LBP_SA like LBP_XX. */ + case LBP_XX: + /* This is arbitrary. */ + prop = LBP_AL; + break; + } - /* Deal with spaces and combining characters. */ - q = p; - if (prop == LBP_SP) - { - /* Don't break just before a space. */ - *p = UC_BREAK_PROHIBITED; - seen_space2 = seen_space; - seen_space = p; - } - else if (prop == LBP_ZW) - { - /* Don't break just before a zero-width space. */ - *p = UC_BREAK_PROHIBITED; - last_prop = LBP_ZW; - seen_space = NULL; - seen_space2 = NULL; - } - else if (prop == LBP_CM) - { - /* Don't break just before a combining character, except immediately after a - zero-width space. */ - if (last_prop == LBP_ZW) - { - /* Break after zero-width space. */ - *p = UC_BREAK_POSSIBLE; - /* A combining character turns a preceding space into LBP_ID. */ - last_prop = LBP_ID; - } - else - { - *p = UC_BREAK_PROHIBITED; - /* A combining character turns a preceding space into LBP_ID. */ - if (seen_space != NULL) - { - q = seen_space; - seen_space = seen_space2; - prop = LBP_ID; - goto lookup_via_table; - } - } - } - else - { - lookup_via_table: - /* prop must be usable as an index for table 7.3 of UTR #14. */ - if (!(prop >= 0 && prop < sizeof (unilbrk_table) / sizeof (unilbrk_table[0]))) - abort (); + /* Deal with spaces and combining characters. */ + q = p; + if (prop == LBP_SP) + { + /* Don't break just before a space. */ + *p = UC_BREAK_PROHIBITED; + seen_space2 = seen_space; + seen_space = p; + } + else if (prop == LBP_ZW) + { + /* Don't break just before a zero-width space. */ + *p = UC_BREAK_PROHIBITED; + last_prop = LBP_ZW; + seen_space = NULL; + seen_space2 = NULL; + } + else if (prop == LBP_CM) + { + /* Don't break just before a combining character, except immediately after a + zero-width space. */ + if (last_prop == LBP_ZW) + { + /* Break after zero-width space. */ + *p = UC_BREAK_POSSIBLE; + /* A combining character turns a preceding space into LBP_ID. */ + last_prop = LBP_ID; + } + else + { + *p = UC_BREAK_PROHIBITED; + /* A combining character turns a preceding space into LBP_ID. */ + if (seen_space != NULL) + { + q = seen_space; + seen_space = seen_space2; + prop = LBP_ID; + goto lookup_via_table; + } + } + } + else + { + lookup_via_table: + /* prop must be usable as an index for table 7.3 of UTR #14. */ + if (!(prop >= 0 && prop < sizeof (unilbrk_table) / sizeof (unilbrk_table[0]))) + abort (); - if (last_prop == LBP_BK) - { - /* Don't break at the beginning of a line. */ - *q = UC_BREAK_PROHIBITED; - } - else if (last_prop == LBP_ZW) - { - /* Break after zero-width space. */ - *q = UC_BREAK_POSSIBLE; - } - else - { - switch (unilbrk_table [last_prop] [prop]) - { - case D: - *q = UC_BREAK_POSSIBLE; - break; - case I: - *q = (seen_space != NULL ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED); - break; - case P: - *q = UC_BREAK_PROHIBITED; - break; - default: - abort (); - } - } - last_prop = prop; - seen_space = NULL; - seen_space2 = NULL; - } - } + if (last_prop == LBP_BK) + { + /* Don't break at the beginning of a line. */ + *q = UC_BREAK_PROHIBITED; + } + else if (last_prop == LBP_ZW) + { + /* Break after zero-width space. */ + *q = UC_BREAK_POSSIBLE; + } + else + { + switch (unilbrk_table [last_prop] [prop]) + { + case D: + *q = UC_BREAK_POSSIBLE; + break; + case I: + *q = (seen_space != NULL ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED); + break; + case P: + *q = UC_BREAK_PROHIBITED; + break; + default: + abort (); + } + } + last_prop = prop; + seen_space = NULL; + seen_space2 = NULL; + } + } s += count; p += count; @@ -183,28 +183,28 @@ read_file (FILE *stream) while (! feof (stream)) { if (size + BUFSIZE > alloc) - { - alloc = alloc + alloc / 2; - if (alloc < size + BUFSIZE) - alloc = size + BUFSIZE; - buf = realloc (buf, alloc); - if (buf == NULL) - { - fprintf (stderr, "out of memory\n"); - exit (1); - } - } + { + alloc = alloc + alloc / 2; + if (alloc < size + BUFSIZE) + alloc = size + BUFSIZE; + buf = realloc (buf, alloc); + if (buf == NULL) + { + fprintf (stderr, "out of memory\n"); + exit (1); + } + } count = fread (buf + size, 1, BUFSIZE, stream); if (count == 0) - { - if (ferror (stream)) - { - perror ("fread"); - exit (1); - } - } + { + if (ferror (stream)) + { + perror ("fread"); + exit (1); + } + } else - size += count; + size += count; } buf = realloc (buf, size + 1); if (buf == NULL) @@ -231,24 +231,24 @@ main (int argc, char * argv[]) u8_possible_linebreaks ((uint8_t *) input, length, "UTF-8", breaks); for (i = 0; i < length; i++) - { - switch (breaks[i]) - { - case UC_BREAK_POSSIBLE: - /* U+2027 in UTF-8 encoding */ - putc (0xe2, stdout); putc (0x80, stdout); putc (0xa7, stdout); - break; - case UC_BREAK_MANDATORY: - /* U+21B2 (or U+21B5) in UTF-8 encoding */ - putc (0xe2, stdout); putc (0x86, stdout); putc (0xb2, stdout); - break; - case UC_BREAK_PROHIBITED: - break; - default: - abort (); - } - putc (input[i], stdout); - } + { + switch (breaks[i]) + { + case UC_BREAK_POSSIBLE: + /* U+2027 in UTF-8 encoding */ + putc (0xe2, stdout); putc (0x80, stdout); putc (0xa7, stdout); + break; + case UC_BREAK_MANDATORY: + /* U+21B2 (or U+21B5) in UTF-8 encoding */ + putc (0xe2, stdout); putc (0x86, stdout); putc (0xb2, stdout); + break; + case UC_BREAK_PROHIBITED: + break; + default: + abort (); + } + putc (input[i], stdout); + } free (breaks); diff --git a/lib/unilbrk/u8-width-linebreaks.c b/lib/unilbrk/u8-width-linebreaks.c index 7e7f2e97..fffe62a2 100644 --- a/lib/unilbrk/u8-width-linebreaks.c +++ b/lib/unilbrk/u8-width-linebreaks.c @@ -1,5 +1,5 @@ /* Line breaking of UTF-8 strings. - Copyright (C) 2001-2003, 2006-2008 Free Software Foundation, Inc. + Copyright (C) 2001-2003, 2006-2010 Free Software Foundation, Inc. Written by Bruno Haible <bruno@clisp.org>, 2001. This program is free software: you can redistribute it and/or modify it @@ -25,9 +25,9 @@ int u8_width_linebreaks (const uint8_t *s, size_t n, - int width, int start_column, int at_end_columns, - const char *o, const char *encoding, - char *p) + int width, int start_column, int at_end_columns, + const char *o, const char *encoding, + char *p) { const uint8_t *s_end; char *last_p; @@ -47,53 +47,53 @@ u8_width_linebreaks (const uint8_t *s, size_t n, /* Respect the override. */ if (o != NULL && *o != UC_BREAK_UNDEFINED) - *p = *o; + *p = *o; if (*p == UC_BREAK_POSSIBLE || *p == UC_BREAK_MANDATORY) - { - /* An atomic piece of text ends here. */ - if (last_p != NULL && last_column + piece_width > width) - { - /* Insert a line break. */ - *last_p = UC_BREAK_POSSIBLE; - last_column = 0; - } - } + { + /* An atomic piece of text ends here. */ + if (last_p != NULL && last_column + piece_width > width) + { + /* Insert a line break. */ + *last_p = UC_BREAK_POSSIBLE; + last_column = 0; + } + } if (*p == UC_BREAK_MANDATORY) - { - /* uc is a line break character. */ - /* Start a new piece at column 0. */ - last_p = NULL; - last_column = 0; - piece_width = 0; - } + { + /* uc is a line break character. */ + /* Start a new piece at column 0. */ + last_p = NULL; + last_column = 0; + piece_width = 0; + } else - { - /* uc is not a line break character. */ - int w; - - if (*p == UC_BREAK_POSSIBLE) - { - /* Start a new piece. */ - last_p = p; - last_column += piece_width; - piece_width = 0; - /* No line break for the moment, may be turned into - UC_BREAK_POSSIBLE later, via last_p. */ - } - - *p = UC_BREAK_PROHIBITED; - - w = uc_width (uc, encoding); - if (w >= 0) /* ignore control characters in the string */ - piece_width += w; - } + { + /* uc is not a line break character. */ + int w; + + if (*p == UC_BREAK_POSSIBLE) + { + /* Start a new piece. */ + last_p = p; + last_column += piece_width; + piece_width = 0; + /* No line break for the moment, may be turned into + UC_BREAK_POSSIBLE later, via last_p. */ + } + + *p = UC_BREAK_PROHIBITED; + + w = uc_width (uc, encoding); + if (w >= 0) /* ignore control characters in the string */ + piece_width += w; + } s += count; p += count; if (o != NULL) - o += count; + o += count; } /* The last atomic piece of text ends here. */ @@ -128,28 +128,28 @@ read_file (FILE *stream) while (! feof (stream)) { if (size + BUFSIZE > alloc) - { - alloc = alloc + alloc / 2; - if (alloc < size + BUFSIZE) - alloc = size + BUFSIZE; - buf = realloc (buf, alloc); - if (buf == NULL) - { - fprintf (stderr, "out of memory\n"); - exit (1); - } - } + { + alloc = alloc + alloc / 2; + if (alloc < size + BUFSIZE) + alloc = size + BUFSIZE; + buf = realloc (buf, alloc); + if (buf == NULL) + { + fprintf (stderr, "out of memory\n"); + exit (1); + } + } count = fread (buf + size, 1, BUFSIZE, stream); if (count == 0) - { - if (ferror (stream)) - { - perror ("fread"); - exit (1); - } - } + { + if (ferror (stream)) + { + perror ("fread"); + exit (1); + } + } else - size += count; + size += count; } buf = realloc (buf, size + 1); if (buf == NULL) @@ -177,21 +177,21 @@ main (int argc, char * argv[]) u8_width_linebreaks ((uint8_t *) input, length, width, 0, 0, NULL, "UTF-8", breaks); for (i = 0; i < length; i++) - { - switch (breaks[i]) - { - case UC_BREAK_POSSIBLE: - putc ('\n', stdout); - break; - case UC_BREAK_MANDATORY: - break; - case UC_BREAK_PROHIBITED: - break; - default: - abort (); - } - putc (input[i], stdout); - } + { + switch (breaks[i]) + { + case UC_BREAK_POSSIBLE: + putc ('\n', stdout); + break; + case UC_BREAK_MANDATORY: + break; + case UC_BREAK_PROHIBITED: + break; + default: + abort (); + } + putc (input[i], stdout); + } free (breaks); diff --git a/lib/unilbrk/ulc-common.c b/lib/unilbrk/ulc-common.c index d035ded7..1ed9c82f 100644 --- a/lib/unilbrk/ulc-common.c +++ b/lib/unilbrk/ulc-common.c @@ -1,5 +1,5 @@ /* Line breaking auxiliary functions. - Copyright (C) 2001-2003, 2006-2008 Free Software Foundation, Inc. + Copyright (C) 2001-2003, 2006-2010 Free Software Foundation, Inc. Written by Bruno Haible <bruno@clisp.org>, 2001. This program is free software: you can redistribute it and/or modify it @@ -43,7 +43,7 @@ is_all_ascii (const char *s, size_t n) unsigned char c = (unsigned char) *s; if (!(c_isprint (c) || c_isspace (c))) - return 0; + return 0; } return 1; } diff --git a/lib/unilbrk/ulc-common.h b/lib/unilbrk/ulc-common.h index 3b481887..bd3c6e44 100644 --- a/lib/unilbrk/ulc-common.h +++ b/lib/unilbrk/ulc-common.h @@ -1,5 +1,5 @@ /* Line breaking auxiliary functions. - Copyright (C) 2001-2003, 2006-2008 Free Software Foundation, Inc. + Copyright (C) 2001-2003, 2006-2010 Free Software Foundation, Inc. Written by Bruno Haible <bruno@clisp.org>, 2001. This program is free software: you can redistribute it and/or modify it diff --git a/lib/unilbrk/ulc-possible-linebreaks.c b/lib/unilbrk/ulc-possible-linebreaks.c index cb952419..eed59b46 100644 --- a/lib/unilbrk/ulc-possible-linebreaks.c +++ b/lib/unilbrk/ulc-possible-linebreaks.c @@ -1,5 +1,5 @@ /* Line breaking of strings. - Copyright (C) 2001-2003, 2006-2009 Free Software Foundation, Inc. + Copyright (C) 2001-2003, 2006-2010 Free Software Foundation, Inc. Written by Bruno Haible <bruno@clisp.org>, 2001. This program is free software: you can redistribute it and/or modify it @@ -42,76 +42,76 @@ void ulc_possible_linebreaks (const char *s, size_t n, const char *encoding, - char *p) + char *p) { if (n > 0) { if (is_utf8_encoding (encoding)) - u8_possible_linebreaks ((const uint8_t *) s, n, encoding, p); + u8_possible_linebreaks ((const uint8_t *) s, n, encoding, p); else - { - /* Convert the string to UTF-8 and build a translation table - from offsets into s to offsets into the translated string. */ - size_t *offsets = (size_t *) malloc (n * sizeof (size_t)); - - if (offsets != NULL) - { - uint8_t *t; - size_t m; - - t = u8_conv_from_encoding (encoding, iconveh_question_mark, - s, n, offsets, NULL, &m); - if (t != NULL) - { - char *q = (char *) (m > 0 ? malloc (m) : NULL); - - if (m == 0 || q != NULL) - { - size_t i; - - /* Determine the possible line breaks of the UTF-8 - string. */ - u8_possible_linebreaks (t, m, encoding, q); - - /* Translate the result back to the original string. */ - memset (p, UC_BREAK_PROHIBITED, n); - for (i = 0; i < n; i++) - if (offsets[i] != (size_t)(-1)) - p[i] = q[offsets[i]]; - - free (q); - free (t); - free (offsets); - return; - } - free (t); - } - free (offsets); - } - - /* Impossible to convert. */ + { + /* Convert the string to UTF-8 and build a translation table + from offsets into s to offsets into the translated string. */ + size_t *offsets = (size_t *) malloc (n * sizeof (size_t)); + + if (offsets != NULL) + { + uint8_t *t; + size_t m; + + t = u8_conv_from_encoding (encoding, iconveh_question_mark, + s, n, offsets, NULL, &m); + if (t != NULL) + { + char *q = (char *) (m > 0 ? malloc (m) : NULL); + + if (m == 0 || q != NULL) + { + size_t i; + + /* Determine the possible line breaks of the UTF-8 + string. */ + u8_possible_linebreaks (t, m, encoding, q); + + /* Translate the result back to the original string. */ + memset (p, UC_BREAK_PROHIBITED, n); + for (i = 0; i < n; i++) + if (offsets[i] != (size_t)(-1)) + p[i] = q[offsets[i]]; + + free (q); + free (t); + free (offsets); + return; + } + free (t); + } + free (offsets); + } + + /* Impossible to convert. */ #if C_CTYPE_ASCII - if (is_all_ascii (s, n)) - { - /* ASCII is a subset of UTF-8. */ - u8_possible_linebreaks ((const uint8_t *) s, n, encoding, p); - return; - } + if (is_all_ascii (s, n)) + { + /* ASCII is a subset of UTF-8. */ + u8_possible_linebreaks ((const uint8_t *) s, n, encoding, p); + return; + } #endif - /* We have a non-ASCII string and cannot convert it. - Don't produce line breaks except those already present in the - input string. All we assume here is that the encoding is - minimally ASCII compatible. */ - { - const char *s_end = s + n; - while (s < s_end) - { - *p = (*s == '\n' ? UC_BREAK_MANDATORY : UC_BREAK_PROHIBITED); - s++; - p++; - } - } - } + /* We have a non-ASCII string and cannot convert it. + Don't produce line breaks except those already present in the + input string. All we assume here is that the encoding is + minimally ASCII compatible. */ + { + const char *s_end = s + n; + while (s < s_end) + { + *p = (*s == '\n' ? UC_BREAK_MANDATORY : UC_BREAK_PROHIBITED); + s++; + p++; + } + } + } } } @@ -136,28 +136,28 @@ read_file (FILE *stream) while (! feof (stream)) { if (size + BUFSIZE > alloc) - { - alloc = alloc + alloc / 2; - if (alloc < size + BUFSIZE) - alloc = size + BUFSIZE; - buf = realloc (buf, alloc); - if (buf == NULL) - { - fprintf (stderr, "out of memory\n"); - exit (1); - } - } + { + alloc = alloc + alloc / 2; + if (alloc < size + BUFSIZE) + alloc = size + BUFSIZE; + buf = realloc (buf, alloc); + if (buf == NULL) + { + fprintf (stderr, "out of memory\n"); + exit (1); + } + } count = fread (buf + size, 1, BUFSIZE, stream); if (count == 0) - { - if (ferror (stream)) - { - perror ("fread"); - exit (1); - } - } + { + if (ferror (stream)) + { + perror ("fread"); + exit (1); + } + } else - size += count; + size += count; } buf = realloc (buf, size + 1); if (buf == NULL) @@ -185,21 +185,21 @@ main (int argc, char * argv[]) ulc_possible_linebreaks (input, length, locale_charset (), breaks); for (i = 0; i < length; i++) - { - switch (breaks[i]) - { - case UC_BREAK_POSSIBLE: - putc ('|', stdout); - break; - case UC_BREAK_MANDATORY: - break; - case UC_BREAK_PROHIBITED: - break; - default: - abort (); - } - putc (input[i], stdout); - } + { + switch (breaks[i]) + { + case UC_BREAK_POSSIBLE: + putc ('|', stdout); + break; + case UC_BREAK_MANDATORY: + break; + case UC_BREAK_PROHIBITED: + break; + default: + abort (); + } + putc (input[i], stdout); + } free (breaks); diff --git a/lib/unilbrk/ulc-width-linebreaks.c b/lib/unilbrk/ulc-width-linebreaks.c index 3b091bf2..16b38816 100644 --- a/lib/unilbrk/ulc-width-linebreaks.c +++ b/lib/unilbrk/ulc-width-linebreaks.c @@ -1,5 +1,5 @@ /* Line breaking of strings. - Copyright (C) 2001-2003, 2006-2009 Free Software Foundation, Inc. + Copyright (C) 2001-2003, 2006-2010 Free Software Foundation, Inc. Written by Bruno Haible <bruno@clisp.org>, 2001. This program is free software: you can redistribute it and/or modify it @@ -42,94 +42,94 @@ int ulc_width_linebreaks (const char *s, size_t n, - int width, int start_column, int at_end_columns, - const char *o, const char *encoding, - char *p) + int width, int start_column, int at_end_columns, + const char *o, const char *encoding, + char *p) { if (n > 0) { if (is_utf8_encoding (encoding)) - return u8_width_linebreaks ((const uint8_t *) s, n, width, start_column, at_end_columns, o, encoding, p); + return u8_width_linebreaks ((const uint8_t *) s, n, width, start_column, at_end_columns, o, encoding, p); else - { - /* Convert the string to UTF-8 and build a translation table - from offsets into s to offsets into the translated string. */ - size_t *offsets = (size_t *) malloc (n * sizeof (size_t)); - - if (offsets != NULL) - { - uint8_t *t; - size_t m; - - t = u8_conv_from_encoding (encoding, iconveh_question_mark, - s, n, offsets, NULL, &m); - if (t != NULL) - { - char *memory = - (char *) (m > 0 ? malloc (m + (o != NULL ? m : 0)) : NULL); - - if (m == 0 || memory != NULL) - { - char *q = (char *) memory; - char *o8 = (o != NULL ? (char *) (q + m) : NULL); - int res_column; - size_t i; - - /* Translate the overrides to the UTF-8 string. */ - if (o != NULL) - { - memset (o8, UC_BREAK_UNDEFINED, m); - for (i = 0; i < n; i++) - if (offsets[i] != (size_t)(-1)) - o8[offsets[i]] = o[i]; - } - - /* Determine the line breaks of the UTF-8 string. */ - res_column = - u8_width_linebreaks (t, m, width, start_column, at_end_columns, o8, encoding, q); - - /* Translate the result back to the original string. */ - memset (p, UC_BREAK_PROHIBITED, n); - for (i = 0; i < n; i++) - if (offsets[i] != (size_t)(-1)) - p[i] = q[offsets[i]]; - - free (memory); - free (t); - free (offsets); - return res_column; - } - free (t); - } - free (offsets); - } - /* Impossible to convert. */ + { + /* Convert the string to UTF-8 and build a translation table + from offsets into s to offsets into the translated string. */ + size_t *offsets = (size_t *) malloc (n * sizeof (size_t)); + + if (offsets != NULL) + { + uint8_t *t; + size_t m; + + t = u8_conv_from_encoding (encoding, iconveh_question_mark, + s, n, offsets, NULL, &m); + if (t != NULL) + { + char *memory = + (char *) (m > 0 ? malloc (m + (o != NULL ? m : 0)) : NULL); + + if (m == 0 || memory != NULL) + { + char *q = (char *) memory; + char *o8 = (o != NULL ? (char *) (q + m) : NULL); + int res_column; + size_t i; + + /* Translate the overrides to the UTF-8 string. */ + if (o != NULL) + { + memset (o8, UC_BREAK_UNDEFINED, m); + for (i = 0; i < n; i++) + if (offsets[i] != (size_t)(-1)) + o8[offsets[i]] = o[i]; + } + + /* Determine the line breaks of the UTF-8 string. */ + res_column = + u8_width_linebreaks (t, m, width, start_column, at_end_columns, o8, encoding, q); + + /* Translate the result back to the original string. */ + memset (p, UC_BREAK_PROHIBITED, n); + for (i = 0; i < n; i++) + if (offsets[i] != (size_t)(-1)) + p[i] = q[offsets[i]]; + + free (memory); + free (t); + free (offsets); + return res_column; + } + free (t); + } + free (offsets); + } + /* Impossible to convert. */ #if C_CTYPE_ASCII - if (is_all_ascii (s, n)) - { - /* ASCII is a subset of UTF-8. */ - return u8_width_linebreaks ((const uint8_t *) s, n, width, start_column, at_end_columns, o, encoding, p); - } + if (is_all_ascii (s, n)) + { + /* ASCII is a subset of UTF-8. */ + return u8_width_linebreaks ((const uint8_t *) s, n, width, start_column, at_end_columns, o, encoding, p); + } #endif - /* We have a non-ASCII string and cannot convert it. - Don't produce line breaks except those already present in the - input string. All we assume here is that the encoding is - minimally ASCII compatible. */ - { - const char *s_end = s + n; - while (s < s_end) - { - *p = ((o != NULL && *o == UC_BREAK_MANDATORY) || *s == '\n' - ? UC_BREAK_MANDATORY - : UC_BREAK_PROHIBITED); - s++; - p++; - if (o != NULL) - o++; - } - /* We cannot compute widths in this case. */ - } - } + /* We have a non-ASCII string and cannot convert it. + Don't produce line breaks except those already present in the + input string. All we assume here is that the encoding is + minimally ASCII compatible. */ + { + const char *s_end = s + n; + while (s < s_end) + { + *p = ((o != NULL && *o == UC_BREAK_MANDATORY) || *s == '\n' + ? UC_BREAK_MANDATORY + : UC_BREAK_PROHIBITED); + s++; + p++; + if (o != NULL) + o++; + } + /* We cannot compute widths in this case. */ + } + } } return start_column; } @@ -154,28 +154,28 @@ read_file (FILE *stream) while (! feof (stream)) { if (size + BUFSIZE > alloc) - { - alloc = alloc + alloc / 2; - if (alloc < size + BUFSIZE) - alloc = size + BUFSIZE; - buf = realloc (buf, alloc); - if (buf == NULL) - { - fprintf (stderr, "out of memory\n"); - exit (1); - } - } + { + alloc = alloc + alloc / 2; + if (alloc < size + BUFSIZE) + alloc = size + BUFSIZE; + buf = realloc (buf, alloc); + if (buf == NULL) + { + fprintf (stderr, "out of memory\n"); + exit (1); + } + } count = fread (buf + size, 1, BUFSIZE, stream); if (count == 0) - { - if (ferror (stream)) - { - perror ("fread"); - exit (1); - } - } + { + if (ferror (stream)) + { + perror ("fread"); + exit (1); + } + } else - size += count; + size += count; } buf = realloc (buf, size + 1); if (buf == NULL) @@ -204,21 +204,21 @@ main (int argc, char * argv[]) ulc_width_linebreaks (input, length, width, 0, 0, NULL, locale_charset (), breaks); for (i = 0; i < length; i++) - { - switch (breaks[i]) - { - case UC_BREAK_POSSIBLE: - putc ('\n', stdout); - break; - case UC_BREAK_MANDATORY: - break; - case UC_BREAK_PROHIBITED: - break; - default: - abort (); - } - putc (input[i], stdout); - } + { + switch (breaks[i]) + { + case UC_BREAK_POSSIBLE: + putc ('\n', stdout); + break; + case UC_BREAK_MANDATORY: + break; + case UC_BREAK_PROHIBITED: + break; + default: + abort (); + } + putc (input[i], stdout); + } free (breaks); |