diff options
author | wlemb <wlemb> | 2003-12-27 05:46:57 +0000 |
---|---|---|
committer | wlemb <wlemb> | 2003-12-27 05:46:57 +0000 |
commit | 2529d328ba5a6b7d45644de8f3883b054e39ce76 (patch) | |
tree | 4ee7fb39e6c28dc5ce6d53ddb829ea37de0b6c53 /src/utils/hpftodit | |
parent | 01e707a2c6a63a77ae127275da490499444d77a7 (diff) | |
download | groff-2529d328ba5a6b7d45644de8f3883b054e39ce76.tar.gz |
hpftodit has been extended to handle TrueType metric files and
more glyphs. See hpftodit.man for more details.
* src/utils/hpftodit/hpftodit.cpp: Include stdio.h, string.h,
ctype.h, and unicode.h.
s/msl/charcode/ everywhere since we now handle Unicode values also.
(equal, NO, YES, MSL, SYMSET, UNICODE, UNICODE): New macros.
Use it where appropriate.
(MULTIPLIER): Replaced with...
(multiplier): New global static variable.
(scale): Updated.
(tag_type): Add more TFM tags.
(tag_name): New array.
(ENUM_TYPE, FLOAT_TYPE): Removed.
(BYTE_TYPE): New value assigned.
(ASCII_TYPE, RATIONAL_TYPE): New enumeration values.
(text_symbol_sets, special_symbol_sets): Extended to cover more
sets.
(check_type): Add return value.
(check_units): Add parameters to get ppi and upem values.
Handle TrueType TFM data.
(output_font_name): New function.
(output_charset): Add parameter to handle TFM type.
Handle TrueType TFMs also.
(em_fract): New macro.
(dump_tags): Be much more verbose and handle more tags.
(dump_ascii, dump_symbol_sets, dump_symbols): New functions.
(hp_msl_to_ucode_name, unicode_to_ucode_name, is_uname): New
functions.
(read_map): Add parameter to handle TFM type.
Handle both MSL and Unicode mappings.
(main): Add two new command line options `-a' and `-q'.
Updated to make use of new functions.
(usage): Updated.
* src/utils/hpftodit/hpuni.cpp: New file.
* src/utils/hpftodit/Makefile.sub, src/utils/hpftodit/hpftodit.man:
Updated.
* src/include/nonposix.h (read) [_MSC_VER]: Define.
Diffstat (limited to 'src/utils/hpftodit')
-rw-r--r-- | src/utils/hpftodit/Makefile.sub | 6 | ||||
-rw-r--r-- | src/utils/hpftodit/hpftodit.cpp | 837 | ||||
-rw-r--r-- | src/utils/hpftodit/hpftodit.man | 202 | ||||
-rw-r--r-- | src/utils/hpftodit/hpuni.cpp | 698 |
4 files changed, 1572 insertions, 171 deletions
diff --git a/src/utils/hpftodit/Makefile.sub b/src/utils/hpftodit/Makefile.sub index d83188c5..6e80b474 100644 --- a/src/utils/hpftodit/Makefile.sub +++ b/src/utils/hpftodit/Makefile.sub @@ -2,5 +2,7 @@ PROG=hpftodit$(EXEEXT) MAN1=hpftodit.n XLIBS=$(LIBGROFF) MLIB=$(LIBM) -OBJS=hpftodit.$(OBJEXT) -CCSRCS=$(srcdir)/hpftodit.cpp +OBJS=hpftodit.$(OBJEXT) \ + hpuni.$(OBJEXT) +CCSRCS=$(srcdir)/hpftodit.cpp \ + $(srcdir)/hpuni.cpp diff --git a/src/utils/hpftodit/hpftodit.cpp b/src/utils/hpftodit/hpftodit.cpp index fe512b61..f5ed8b36 100644 --- a/src/utils/hpftodit/hpftodit.cpp +++ b/src/utils/hpftodit/hpftodit.cpp @@ -20,17 +20,17 @@ Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ /* TODO -put human readable font name in device file devise new names for useful characters -use --- for unnamed characters option to specify symbol sets to look in -make it work with TrueType fonts put filename in error messages (or fix lib) */ #include "lib.h" +#include <stdio.h> #include <stdlib.h> +#include <string.h> +#include <ctype.h> #include <math.h> #include <errno.h> #include "assert.h" @@ -39,17 +39,29 @@ put filename in error messages (or fix lib) #include "error.h" #include "cset.h" #include "nonposix.h" +#include "unicode.h" extern "C" const char *Version_string; +extern const char *hp_msl_to_unicode_code(const char *); #define SIZEOF(v) (sizeof(v)/sizeof(v[0])) +#define equal(a, b) (strcmp(a, b) == 0) -const int MULTIPLIER = 3; +#define NO 0 +#define YES 1 + +#define MSL 0 +#define SYMSET 1 +#define UNICODE 2 + +#define UNNAMED "---" + +static double multiplier = 3.0; // make Agfa-based unitwidth an integer inline int scale(int n) { - return n * MULTIPLIER; + return int(n * multiplier + 0.5); } // tags in TFM file @@ -57,39 +69,67 @@ int scale(int n) enum tag_type { min_tag = 400, type_tag = 400, + copyright_tag = 401, + comment_tag = 402, + charcode_tag = 403, // MSL for Intellifont, Unicode for TrueType symbol_set_tag = 404, - msl_tag = 403, + unique_identifier_tag = 405, inches_per_point_tag = 406, + nominal_point_size_tag = 407, design_units_per_em_tag = 408, posture_tag = 409, + type_structure_tag = 410, stroke_weight_tag = 411, spacing_tag = 412, slant_tag = 413, appearance_width_tag = 414, + serif_style_tag = 415, + font_name_tag = 417, + typeface_source_tag = 418, + average_width_tag = 419, + max_width_tag = 420, word_spacing_tag = 421, + recommended_line_spacing_tag = 422, + cap_height_tag = 423, x_height_tag = 424, + max_ascent_tag = 425, + max_descent_tag = 426, lower_ascent_tag = 427, lower_descent_tag = 428, + underscore_depth_tag = 429, + underscore_thickness_tag = 430, + uppercase_accent_height_tag = 431, + lowercase_accent_height_tag = 432, width_tag = 433, + vertical_escapement_tag = 434, left_extent_tag = 435, right_extent_tag = 436, ascent_tag = 437, descent_tag = 438, pair_kern_tag = 439, + sector_kern_tag = 440, + track_kern_tag = 441, typeface_tag = 442, + panose_tag = 443, max_tag = 443 - }; +}; -// types in TFM file +const char *tag_name[] = { + "Symbol Set", + "Font Type" // MSL for Intellifont, Unicode for TrueType +}; +// types in TFM file enum { - ENUM_TYPE = 1, - BYTE_TYPE = 2, + BYTE_TYPE = 1, + ASCII_TYPE = 2, // NUL-terminated string USHORT_TYPE = 3, - FLOAT_TYPE = 5, - SIGNED_SHORT_TYPE = 17 - }; - + LONG_TYPE = 4, // unused + RATIONAL_TYPE = 5, // 8-byte numerator + 8-byte denominator + SIGNED_BYTE_TYPE = 16, // unused + SIGNED_SHORT_TYPE = 17, + SIGNED_LONG_TYPE = 18 // unused +}; typedef unsigned char byte; typedef unsigned short uint16; @@ -119,7 +159,7 @@ struct entry { }; struct char_info { - uint16 msl; + uint16 charcode; uint16 width; int16 ascent; int16 descent; @@ -145,44 +185,102 @@ struct symbol_set { #define SYMBOL_SET(n, c) ((n) * 32 + ((c) - 64)) +// change this to '1' to compare results with original version +#if 0 uint16 text_symbol_sets[] = { SYMBOL_SET(0, 'N'), // Latin 1 SYMBOL_SET(6, 'J'), // Microsoft Publishing SYMBOL_SET(2, 'N'), // Latin 2 0 - }; +}; uint16 special_symbol_sets[] = { SYMBOL_SET(8, 'M'), SYMBOL_SET(5, 'M'), SYMBOL_SET(15, 'U'), 0 - }; +}; +#else +uint16 text_symbol_sets[] = { + SYMBOL_SET(19, 'U'), // Windows Latin 1 ("ANSI", code page 1252) + SYMBOL_SET(7, 'J'), // Desktop + SYMBOL_SET(6, 'J'), // Microsoft Publishing + SYMBOL_SET(9, 'E'), // Windows Latin 2, Code Page 1250 + SYMBOL_SET(2, 'N'), // Latin 2 (subset of 9M, + // so we should never get here) + SYMBOL_SET(0, 'N'), // Latin 1 (subset of 19U, + // so we should never get here) + SYMBOL_SET(8, 'U'), // HP Roman 8 + SYMBOL_SET(10, 'J'), // PS Standard + SYMBOL_SET(9, 'U'), // Windows 3.0 "ANSI" + +#if 0 + SYMBOL_SET(13, 'J'), // Ventura International + SYMBOL_SET(6, 'M'), // Ventura Math + SYMBOL_SET(14, 'J'), // Ventura US + SYMBOL_SET(5, 'T'), // Code Page 1254 + SYMBOL_SET(0, 'D'), // ISO 60, 7-bit Norwegian version 1 + SYMBOL_SET(5, 'N'), // ISO 8859-9, Latin 5 + SYMBOL_SET(1, 'F'), // ISO 69, 7-bit French + SYMBOL_SET(1, 'G'), // ISO 21, 7-bit German + SYMBOL_SET(0, 'I'), // ISO 15, 7-bit Italian + SYMBOL_SET(1, 'U'), // Legal + SYMBOL_SET(12, 'J'), // MC Text + SYMBOL_SET(10, 'U'), // PC Code Page 437 + SYMBOL_SET(11, 'U'), // PC Code Page 437N + SYMBOL_SET(17, 'U'), // PC Code Page 852 + SYMBOL_SET(12, 'U'), // PC Code Page 850 + SYMBOL_SET(9, 'T'), // PC Code Page 437T + SYMBOL_SET(2, 'S'), // ISO 17, 7-bit Spanish + SYMBOL_SET(0, 'S'), // ISO 11, 7-bit Swedish + SYMBOL_SET(1, 'E'), // ISO 4, 7-bit UK English + SYMBOL_SET(0, 'U'), // ISO 6, 7-bit ASCII English +#endif + 0 +}; + +uint16 special_symbol_sets[] = { + SYMBOL_SET(8, 'M'), // Math 8 + SYMBOL_SET(5, 'M'), // PS Math + SYMBOL_SET(15, 'U'), // Pi font + SYMBOL_SET(19, 'M'), // Symbol font + 0 +}; +#endif entry tags[max_tag + 1 - min_tag]; char_info *char_table; -uint32 nchars; +uint32 nchars = 0; -unsigned int msl_name_table_size = 0; -name_list **msl_name_table = 0; +unsigned int charcode_name_table_size = 0; +name_list **charcode_name_table = NULL; unsigned int n_symbol_sets; symbol_set *symbol_set_table; -static int special_flag = 0; -static int italic_flag = 0; +static int special_flag = NO; // not a special font +static int italic_flag = NO; // don't add italic correction static int italic_sep; +static int all_flag = NO; // don't include glyphs not in mapfile +static int quiet_flag = NO; // don't suppress warnings about symbols not found -static void usage(FILE *stream); +static char *hp_msl_to_ucode_name(int); +static char *unicode_to_ucode_name(int); +static int is_uname(char *); +static void usage(FILE *); static void usage(); static const char *xbasename(const char *); static void read_tags(File &); -static void check_type(); -static void check_units(File &); -static int read_map(const char *); +static int check_type(); +static void check_units(File &, const int, double *, double *); +static int read_map(const char *, const int); static void require_tag(tag_type); -static void dump_tags(File &f); +static void dump_ascii(File &, tag_type); +static void dump_tags(File &); +static void dump_symbol_sets(File &); +static void dump_symbols(int); +static void output_font_name(File &); static void output_spacewidth(); static void output_pclweight(); static void output_pclproportional(); @@ -192,8 +290,8 @@ static void output_slant(); static void output_ligatures(); static void read_symbol_sets(File &); static void read_and_output_kernpairs(File &); -static void output_charset(); -static void read_char_table(File &f); +static void output_charset(const int); +static void read_char_table(File &); inline entry &tag_info(tag_type t) @@ -206,25 +304,36 @@ int main(int argc, char **argv) program_name = argv[0]; int opt; - int debug_flag = 0; + int debug_flag = NO; + int res = 1200; // PCL unit of measure for cursor moves + int scalesize = 4; // LaserJet 4 only allows 1/4 point increments + int unitwidth = 6350; + double ppi; // points per inch + double upem; // design units per em static const struct option long_options[] = { { "help", no_argument, 0, CHAR_MAX + 1 }, { "version", no_argument, 0, 'v' }, { NULL, 0, 0, 0 } }; - while ((opt = getopt_long(argc, argv, "dsvi:", long_options, NULL)) != EOF) { + while ((opt = getopt_long(argc, argv, "adsqvi:", long_options, NULL)) != EOF) { switch (opt) { + case 'a': + all_flag = YES; + break; case 'd': - debug_flag = 1; + debug_flag = YES; break; case 's': - special_flag = 1; + special_flag = YES; break; case 'i': - italic_flag = 1; - italic_sep = atoi(optarg); + italic_flag = YES; + italic_sep = atoi(optarg); // design units break; + case 'q': + quiet_flag = YES; // suppress warnings about symbols not found + break; case 'v': { printf("GNU hpftodit (groff) version %s\n", Version_string); @@ -242,44 +351,69 @@ int main(int argc, char **argv) assert(0); } } - if (argc - optind != 3) + + if (debug_flag && argc - optind < 1) + usage(); + else if (!debug_flag && argc - optind != 3) usage(); File f(argv[optind]); - if (!read_map(argv[optind + 1])) - exit(1); - current_filename = 0; - current_lineno = -1; // no line numbers - if (freopen(argv[optind + 2], "w", stdout) == 0) - fatal("cannot open `%1': %2", argv[optind + 2], strerror(errno)); - current_filename = argv[optind]; - printf("name %s\n", xbasename(argv[optind + 2])); - if (special_flag) - printf("special\n"); read_tags(f); - check_type(); - check_units(f); + int tfm_type = check_type(); if (debug_flag) dump_tags(f); + else if (!read_map(argv[optind + 1], tfm_type)) + exit(1); + current_filename = NULL; + current_lineno = -1; // no line numbers + if (!debug_flag && !equal(argv[optind + 2], "-")) + if (freopen(argv[optind + 2], "w", stdout) == NULL) + fatal("cannot open `%1': %2", argv[optind + 2], strerror(errno)); + current_filename = argv[optind]; + + check_units(f, tfm_type, &ppi, &upem); + if (tfm_type == UNICODE) // don't calculate for Intellifont TFMs + multiplier = double(res) / upem / ppi * unitwidth / scalesize; + if (italic_flag) + // convert from thousandths of an em to design units + italic_sep = int(italic_sep * upem / 1000 + 0.5); + read_char_table(f); - output_spacewidth(); - output_slant(); - read_and_output_pcltypeface(f); - output_pclproportional(); - output_pclweight(); - output_pclstyle(); + if (nchars == 0) + fatal("no characters"); + + if (!debug_flag) { + output_font_name(f); + printf("name %s\n", xbasename(argv[optind + 2])); + if (special_flag) + printf("special\n"); + output_spacewidth(); + output_slant(); + read_and_output_pcltypeface(f); + output_pclproportional(); + output_pclweight(); + output_pclstyle(); + } read_symbol_sets(f); - output_ligatures(); - read_and_output_kernpairs(f); - output_charset(); + if (debug_flag) { + printf("Symbols:\n"); + dump_symbols(tfm_type); + } + else { + output_ligatures(); + read_and_output_kernpairs(f); + output_charset(tfm_type); + } return 0; } static void usage(FILE *stream) { - fprintf(stream, "usage: %s [-s] [-i n] tfm_file map_file output_font\n", + fprintf(stream, + "usage: %s [-s] [-a] [-q] [-i n] tfm_file map_file output_font\n", program_name); } + static void usage() { @@ -319,7 +453,7 @@ void File::skip(int n) void File::seek(uint32 n) { - if ((uint32)(end_ - buf_) < n) + if (uint32(end_ - buf_) < n) fatal("unexpected end of file"); ptr_ = buf_ + n; } @@ -372,31 +506,40 @@ void read_tags(File &f) } static -void check_type() +int check_type() { require_tag(type_tag); - if (tag_info(type_tag).value != 0) { - if (tag_info(type_tag).value == 2) - fatal("cannot handle TrueType tfm files"); - fatal("unknown type tag %1", int(tag_info(type_tag).value)); + int tfm_type = tag_info(type_tag).value; + switch (tfm_type) { + case MSL: + case UNICODE: + break; + case SYMSET: + fatal("cannot handle Symbol Set TFM files"); + break; + default: + fatal("unknown type tag %1", tfm_type); } + return tfm_type; } static -void check_units(File &f) +void check_units(File &f, const int tfm_type, double *ppi, double *upem) { require_tag(design_units_per_em_tag); f.seek(tag_info(design_units_per_em_tag).value); uint32 num = f.get_uint32(); uint32 den = f.get_uint32(); - if (num != 8782 || den != 1) + if (tfm_type == MSL && (num != 8782 || den != 1)) fatal("design units per em != 8782/1"); + *upem = double(num) / den; require_tag(inches_per_point_tag); f.seek(tag_info(inches_per_point_tag).value); num = f.get_uint32(); den = f.get_uint32(); - if (num != 100 || den != 7231) + if (tfm_type == MSL && (num != 100 || den != 7231)) fatal("inches per point not 100/7231"); + *ppi = double(den) / num; } static @@ -406,6 +549,36 @@ void require_tag(tag_type t) fatal("tag %1 missing", int(t)); } +// put a human-readable font name in the file +static +void output_font_name(File &f) +{ + char *p; + + if (!tag_info(font_name_tag).present) + return; + int count = tag_info(font_name_tag).count; + char *font_name = new char[count]; + + if (count > 4) { // value is a file offset to the string + f.seek(tag_info(font_name_tag).value); + int n = count; + p = font_name; + while (--n) + *p++ = f.get_byte(); + } + else // value contains the string + sprintf(font_name, "%.*s", count, (char*)(tag_info(font_name_tag).value)); + + // remove any trailing space + p = font_name + count - 1; + while (csspace(*--p)) + ; + *(p + 1) = '\0'; + printf("# %s\n", font_name); + delete font_name; +} + static void output_spacewidth() { @@ -422,10 +595,11 @@ void read_symbol_sets(File &f) unsigned int i; for (i = 0; i < n_symbol_sets; i++) { f.seek(tag_info(symbol_set_tag).value + i*14); - (void)f.get_uint32(); - uint32 off1 = f.get_uint32(); - uint32 off2 = f.get_uint32(); - (void)f.get_uint16(); // what's this for? + (void)f.get_uint32(); // offset to symbol set name + uint32 off1 = f.get_uint32(); // offset to selection string + uint32 off2 = f.get_uint32(); // offset to symbol set index array + (void)f.get_uint16(); // index array length + // (why is this needed?) f.seek(off1); unsigned int j; uint16 kind = 0; @@ -440,6 +614,7 @@ void read_symbol_sets(File &f) for (j = 0; j < 256; j++) symbol_set_table[i].index[j] = f.get_uint16(); } + for (i = 0; i < nchars; i++) char_table[i].symbol_set = NO_SYMBOL_SET; @@ -467,14 +642,14 @@ void read_symbol_sets(File &f) static void read_char_table(File &f) { - require_tag(msl_tag); - nchars = tag_info(msl_tag).count; + require_tag(charcode_tag); + nchars = tag_info(charcode_tag).count; char_table = new char_info[nchars]; - f.seek(tag_info(msl_tag).value); + f.seek(tag_info(charcode_tag).value); uint32 i; for (i = 0; i < nchars; i++) - char_table[i].msl = f.get_uint16(); + char_table[i].charcode = f.get_uint16(); require_tag(width_tag); f.seek(tag_info(width_tag).value); @@ -596,10 +771,10 @@ void output_ligatures() unsigned ligature_mask = 0; unsigned int i; for (i = 0; i < nchars; i++) { - uint16 msl = char_table[i].msl; - if (msl < msl_name_table_size + uint16 charcode = char_table[i].charcode; + if (charcode < charcode_name_table_size && char_table[i].symbol_set != NO_SYMBOL_SET) { - for (name_list *p = msl_name_table[msl]; p; p = p->next) + for (name_list *p = charcode_name_table[charcode]; p; p = p->next) for (unsigned int j = 0; j < SIZEOF(ligature_chars); j++) if (strcmp(p->name, ligature_chars[j]) == 0) { ligature_mask |= 1 << j; @@ -629,22 +804,23 @@ void read_and_output_kernpairs(File &f) int16 val = int16(f.get_uint16()); if (char_table[i1].symbol_set != NO_SYMBOL_SET && char_table[i2].symbol_set != NO_SYMBOL_SET - && char_table[i1].msl < msl_name_table_size - && char_table[i2].msl < msl_name_table_size) { - for (name_list *p = msl_name_table[char_table[i1].msl]; + && char_table[i1].charcode < charcode_name_table_size + && char_table[i2].charcode < charcode_name_table_size) { + for (name_list *p = charcode_name_table[char_table[i1].charcode]; p; p = p->next) - for (name_list *q = msl_name_table[char_table[i2].msl]; + for (name_list *q = charcode_name_table[char_table[i2].charcode]; q; q = q->next) - printf("%s %s %d\n", p->name, q->name, scale(val)); + if (!equal(p->name, UNNAMED) && !equal(q->name, UNNAMED)) + printf("%s %s %d\n", p->name, q->name, scale(val)); } } } } static -void output_charset() +void output_charset(const int tfm_type) { require_tag(slant_tag); double slant_angle = int16(tag_info(slant_tag).value)*PI/18000.0; @@ -657,20 +833,30 @@ void output_charset() printf("charset\n"); unsigned int i; for (i = 0; i < nchars; i++) { - uint16 msl = char_table[i].msl; - if (msl < msl_name_table_size - && msl_name_table[msl]) { - if (char_table[i].symbol_set != NO_SYMBOL_SET) { - printf("%s\t%d,%d", - msl_name_table[msl]->name, - scale(char_table[i].width), - scale(char_table[i].ascent)); - int depth = scale(- char_table[i].descent); + uint16 charcode = char_table[i].charcode; + + // the TFM supports the character + if (char_table[i].symbol_set != NO_SYMBOL_SET) { + // the character was in the map file + if (charcode < charcode_name_table_size && charcode_name_table[charcode]) + printf("%s", charcode_name_table[charcode]->name); + else if (!all_flag) + continue; + else if (tfm_type == MSL) + printf(hp_msl_to_ucode_name(charcode)); + else + printf(unicode_to_ucode_name(charcode)); + + printf("\t%d,%d", + scale(char_table[i].width), scale(char_table[i].ascent)); + + int depth = scale(-char_table[i].descent); if (depth < 0) depth = 0; int italic_correction = 0; int left_italic_correction = 0; int subscript_correction = 0; + if (italic_flag) { italic_correction = scale(char_table[i].right_extent - char_table[i].width @@ -684,6 +870,7 @@ void output_charset() left_italic_correction = scale(italic_sep - char_table[i].left_extent); } + if (subscript_correction != 0) printf(",%d,%d,%d,%d", depth, italic_correction, left_italic_correction, @@ -696,45 +883,390 @@ void output_charset() printf(",%d", depth); // This is fairly arbitrary. Fortunately it doesn't much matter. unsigned type = 0; - if (char_table[i].ascent > (int16(tag_info(lower_ascent_tag).value)*9)/10) + if (char_table[i].ascent > int16(tag_info(lower_ascent_tag).value)*9/10) type |= 2; - if (char_table[i].descent < (int16(tag_info(lower_descent_tag).value)*9)/10) + if (char_table[i].descent < int16(tag_info(lower_descent_tag).value)*9/10) type |= 1; - printf("\t%d\t%d\n", - type, + printf("\t%d\t%d", type, char_table[i].symbol_set*256 + char_table[i].code); - for (name_list *p = msl_name_table[msl]->next; p; p = p->next) - printf("%s\t\"\n", p->name); + + if (tfm_type == UNICODE) { + if (charcode >= 0xE000 && charcode <= 0xF8FF) + printf("\t\t-- HP PUA U+%04X\n", charcode); + else + printf("\t\t-- U+%04X\n", charcode); + } + else + printf("\t\t-- HP MSL %4d\n", charcode); + + if (charcode < charcode_name_table_size + && charcode_name_table[charcode]) + for (name_list *p = charcode_name_table[charcode]->next; + p; p = p->next) + printf("%s\t\"\n", p->name); } - else - warning("MSL %1 not in any of the searched symbol sets", msl); + // warnings about characters in mapfile not found in TFM + else if (charcode < charcode_name_table_size + && charcode_name_table[charcode]) { + char *name = charcode_name_table[charcode]->name; + // don't warn about Unicode or unnamed glyphs + // that aren't in the the TFM file + if (tfm_type == UNICODE && !quiet_flag && !equal(name, UNNAMED) + && !is_uname(name)) + fprintf(stderr, + "%s: warning: symbol U+%04X (%s) not in any of the searched symbol sets\n", + program_name, charcode, name); + else if (!quiet_flag && !equal(name, UNNAMED) && !is_uname(name)) + warning("MSL %1 (%2) not in any of the searched symbol sets", + charcode, name); } } } +#define em_fract(a) (upem >= 0 ? double(a)/upem : 0) + static void dump_tags(File &f) { - int i; - for (i = min_tag; i <= max_tag; i++) { + double upem = -1.0; + + printf("TFM tags\n" + "\n" + "tag# type count value\n" + "---------------------\n"); + + for (int i = min_tag; i <= max_tag; i++) { enum tag_type t = tag_type(i); if (tag_info(t).present) { - fprintf(stderr, - "%d %d %d %d\n", i, tag_info(t).type, tag_info(t).count, - tag_info(t).value); - if (tag_info(t).type == FLOAT_TYPE - && tag_info(t).count == 1) { - f.seek(tag_info(t).value); - uint32 num = f.get_uint32(); - uint32 den = f.get_uint32(); - fprintf(stderr, "(%u/%u = %g)\n", num, den, (double)num/den); + printf("%4d %4d %5d", i, tag_info(t).type, tag_info(t).count); + switch (tag_info(t).type) { + case BYTE_TYPE: + case USHORT_TYPE: + printf(" %5u", tag_info(t).value); + switch (i) { + case type_tag: + printf(" Font Type "); + switch (tag_info(t).value) { + case MSL: + case SYMSET: + printf("(Intellifont)"); + break; + case UNICODE: + printf("(TrueType)"); + } + break; + case charcode_tag: + printf(" Number of Symbols (%u)", tag_info(t).count); + break; + case symbol_set_tag: + printf(" Symbol Sets (%u): ", + tag_info(symbol_set_tag).count / 14); + dump_symbol_sets(f); + break; + case type_structure_tag: + printf(" Type Structure (%u)", tag_info(t).value); + break; + case stroke_weight_tag: + printf(" Stroke Weight (%u)", tag_info(t).value); + break; + case spacing_tag: + printf(" Spacing "); + switch (tag_info(t).value) { + case 0: + printf("(Proportional)"); + break; + case 1: + printf("(Fixed Pitch: %u DU: %.2f em)", tag_info(t).value, + em_fract(tag_info(t).value)); + break; + } + break; + case appearance_width_tag: + printf(" Appearance Width (%u)", tag_info(t).value); + break; + case serif_style_tag: + printf(" Serif Style (%u)", tag_info(t).value); + break; + case max_width_tag: + printf(" Maximum Width (%u DU: %.2f em)", tag_info(t).value, + em_fract(tag_info(t).value)); + break; + case word_spacing_tag: + printf(" Interword Spacing (%u DU: %.2f em)", tag_info(t).value, + em_fract(tag_info(t).value)); + break; + case recommended_line_spacing_tag: + printf(" Recommended Line Spacing (%u DU: %.2f em)", tag_info(t).value, + em_fract(tag_info(t).value)); + break; + case x_height_tag: + printf(" x-Height (%u DU: %.2f em)", tag_info(t).value, + em_fract(tag_info(t).value)); + break; + case cap_height_tag: + printf(" Cap Height (%u DU: %.2f em)", tag_info(t).value, + em_fract(tag_info(t).value)); + break; + case max_ascent_tag: + printf(" Maximum Ascent (%u DU: %.2f em)", tag_info(t).value, + em_fract(tag_info(t).value)); + break; + case lower_ascent_tag: + printf(" Lowercase Ascent (%u DU: %.2f em)", tag_info(t).value, + em_fract(tag_info(t).value)); + break; + case underscore_thickness_tag: + printf(" Underscore Thickness (%u DU: %.2f em)", tag_info(t).value, + em_fract(tag_info(t).value)); + break; + case uppercase_accent_height_tag: + printf(" Uppercase Accent Height (%u DU: %.2f em)", tag_info(t).value, + em_fract(tag_info(t).value)); + break; + case lowercase_accent_height_tag: + printf(" Lowercase Accent Height (%u DU: %.2f em)", tag_info(t).value, + em_fract(tag_info(t).value)); + break; + case width_tag: + printf(" Horizontal Escapement array"); + break; + case vertical_escapement_tag: + printf(" Vertical Escapement array"); + break; + case right_extent_tag: + printf(" Right Extent array"); + break; + case ascent_tag: + printf(" Character Ascent array"); + break; + case pair_kern_tag: + f.seek(tag_info(t).value); + printf(" Kern Pairs (%u)", f.get_uint16()); + break; + case panose_tag: + printf(" PANOSE Classification array"); + break; + } + break; + case SIGNED_SHORT_TYPE: + printf(" %5d", int16(tag_info(t).value)); + switch (i) { + case slant_tag: + printf(" Slant (%.2f degrees)", double(tag_info(t).value) / 100); + break; + case max_descent_tag: + printf(" Maximum Descent (%d DU: %.2f em)", int16(tag_info(t).value), + em_fract(int16(tag_info(t).value))); + break; + case lower_descent_tag: + printf(" Lowercase Descent (%d DU: %.2f em)", int16(tag_info(t).value), + em_fract(int16(tag_info(t).value))); + break; + case underscore_depth_tag: + printf(" Underscore Depth (%d DU: %.2f em)", int16(tag_info(t).value), + em_fract(int16(tag_info(t).value))); + break; + case left_extent_tag: + printf(" Left Extent array"); + break; + // both signed and unsigned do exist! + case ascent_tag: + printf(" Character Ascent array"); + break; + case descent_tag: + printf(" Character Descent array"); + break; + } + break; + case RATIONAL_TYPE: + printf(" %5u", tag_info(t).value); + switch (i) { + case inches_per_point_tag: + printf(" Inches per Point"); + break; + case nominal_point_size_tag: + printf(" Nominal Point Size"); + break; + case design_units_per_em_tag: + printf(" Design Units per Em"); + break; + case average_width_tag: + printf(" Average Width"); + break; + } + if (tag_info(t).count == 1) { + f.seek(tag_info(t).value); + uint32 num = f.get_uint32(); + uint32 den = f.get_uint32(); + if (i == design_units_per_em_tag) + upem = double(num) / den; + printf(" (%u/%u = %g)", num, den, double(num)/den); + } + break; + case ASCII_TYPE: + printf(" %5u ", tag_info(t).value); + switch (i) { + case comment_tag: + printf("Comment "); + break; + case copyright_tag: + printf("Copyright "); + break; + case unique_identifier_tag: + printf("Unique ID "); + break; + case font_name_tag: + printf("Typeface Name "); + break; + case typeface_source_tag: + printf("Typeface Source "); + break; + case typeface_tag: + printf("PCL Typeface "); + break; + } + dump_ascii(f, t); } + putchar('\n'); + } + } + putchar('\n'); +} +#undef em_fract + +static +void dump_ascii(File &f, tag_type t) +{ + putchar('"'); + if (tag_info(t).count > 4) { + int count = tag_info(t).count; + f.seek(tag_info(t).value); + while (--count) + printf("%c", f.get_byte()); + } + else + printf("%.4s", (char*)(tag_info(t).value)); + putchar('"'); +} + +static +void dump_symbol_sets(File &f) +{ + uint32 symbol_set_dir_length = tag_info(symbol_set_tag).count; + uint32 n_symbol_sets = symbol_set_dir_length / 14; + + for (uint32 i = 0; i < n_symbol_sets; i++) { + f.seek(tag_info(symbol_set_tag).value + i * 14); + (void)f.get_uint32(); // offset to symbol set name + uint32 off1 = f.get_uint32(); // offset to selection string + uint32 off2 = f.get_uint32(); // offset to symbol set index array + f.seek(off1); + for (uint32 j = 0; j < off2 - off1; j++) { + unsigned char c = f.get_byte(); + if ('0' <= c && c <= '9') + putchar(c); + else if ('A' <= c && c <= 'Z') + printf(i < n_symbol_sets - 1 ? "%c," : "%c", c); } } } +static +void dump_symbols(int tfm_type) +{ + for (uint32 i = 0; i < nchars; i++) { + uint16 charcode = char_table[i].charcode; + if (charcode < charcode_name_table_size + && charcode_name_table[charcode]) { + if (char_table[i].symbol_set != NO_SYMBOL_SET) { + printf(tfm_type == UNICODE ? "%4d (%04x) %d (%d%c)\t%s\n" + : "%4d (%4d) %d (%d%c)\t%s\n" , + i, charcode, char_table[i].symbol_set, + char_table[i].symbol_set / 32, + (char_table[i].symbol_set % 32) + 64, + charcode_name_table[charcode]->name); + } + } + else + printf(tfm_type == UNICODE ? "%4d (U+%04X)\n" + : "%4d (HP MSL %4d)\n", + i, charcode); + } +} + +static char * +hp_msl_to_ucode_name(int msl) +{ + char codestr[8]; + + sprintf(codestr, "%d", msl); + const char *ustr = hp_msl_to_unicode_code(codestr); + if (ustr == NULL) + ustr = UNNAMED; + else { + char *nonum; + int ucode = int(strtol(ustr, &nonum, 16)); + // don't allow PUA code points as Unicode names + if (ucode >= 0xE000 && ucode <= 0xF8FF) + ustr = UNNAMED; + } + if (!equal(ustr, UNNAMED)) { + const char *uname_decomposed = decompose_unicode(ustr); + if (uname_decomposed) + // 1st char is the number of components + ustr = uname_decomposed + 1; + } + char *value = new char[strlen(ustr) + 1]; + sprintf(value, equal(ustr, UNNAMED) ? ustr : "u%s", ustr); + return value; +} + +static char * +unicode_to_ucode_name(int ucode) +{ + const char *ustr; + char codestr[8]; + + // don't allow PUA code points as Unicode names + if (ucode >= 0xE000 && ucode <= 0xF8FF) + ustr = UNNAMED; + else { + sprintf(codestr, "%04X", ucode); + ustr = codestr; + } + if (!equal(ustr, UNNAMED)) { + const char *uname_decomposed = decompose_unicode(ustr); + if (uname_decomposed) + // 1st char is the number of components + ustr = uname_decomposed + 1; + } + char *value = new char[strlen(ustr) + 1]; + sprintf(value, equal(ustr, UNNAMED) ? ustr : "u%s", ustr); + return value; +} + +static int +is_uname(char *name) +{ + size_t i; + size_t len = strlen(name); + if (len % 5) + return 0; + + if (name[0] != 'u') + return 0; + for (i = 1; i < 4; i++) + if (!csxdigit(name[i])) + return 0; + for (i = 5; i < len; i++) + if (i % 5 ? !csxdigit(name[i]) : name[i] != '_') + return 0; + + return 1; +} + static -int read_map(const char *file) +int read_map(const char *file, const int tfm_type) { errno = 0; FILE *fp = fopen(file, "r"); @@ -745,6 +1277,7 @@ int read_map(const char *file) current_filename = file; char buf[512]; current_lineno = 0; + char *nonum; while (fgets(buf, int(sizeof(buf)), fp)) { current_lineno++; char *ptr = buf; @@ -755,37 +1288,73 @@ int read_map(const char *file) ptr = strtok(ptr, " \n\t"); if (!ptr) continue; - int n; - if (sscanf(ptr, "%d", &n) != 1) { - error("bad map file"); + + int msl_code = int(strtol(ptr, &nonum, 10)); + if (*nonum != '\0') { + if (csxdigit(*nonum)) + error("bad MSL map: got hex code (%1)", ptr); + else if (ptr == nonum) + error("bad MSL map: bad MSL code (%1)", ptr); + else + error("bad MSL map"); fclose(fp); return 0; } - if (n < 0) { - error("negative code"); + + ptr = strtok(NULL, " \n\t"); + if (!ptr) + continue; + int unicode = int(strtol(ptr, &nonum, 16)); + if (*nonum != '\0') { + if (ptr == nonum) + error("bad Unicode value (%1)", ptr); + else + error("bad Unicode map"); fclose(fp); return 0; } - if ((size_t)n >= msl_name_table_size) { - size_t old_size = msl_name_table_size; - name_list **old_table = msl_name_table; - msl_name_table_size = n + 256; - msl_name_table = new name_list *[msl_name_table_size]; - if (old_table) { - memcpy(msl_name_table, old_table, old_size*sizeof(name_list *)); - a_delete old_table; - } - for (size_t i = old_size; i < msl_name_table_size; i++) - msl_name_table[i] = 0; + if (strlen(ptr) != 4) { + error("bad Unicode value (%1)", ptr); + return 0; + } + + int n = tfm_type == MSL ? msl_code : unicode; + if (tfm_type == UNICODE && n > 0xFFFF) { + // greatest value supported by TFM files + error("bad Unicode value (%1): greatest value is 0xFFFF", ptr); + fclose(fp); + return 0; } - ptr = strtok(0, " \n\t"); - if (!ptr) { - error("missing names"); + else if (n < 0) { + error("negative code value (%1)", ptr); fclose(fp); return 0; } - for (; ptr; ptr = strtok(0, " \n\t")) - msl_name_table[n] = new name_list(ptr, msl_name_table[n]); + + ptr = strtok(NULL, " \n\t"); + if (!ptr) { // groff name + error("missing name(s)"); + fclose(fp); + return 0; + } + else if (is_uname(ptr)) + ptr = unicode_to_ucode_name(strtol(ptr + 1, &nonum, 16)); + + if (size_t(n) >= charcode_name_table_size) { + size_t old_size = charcode_name_table_size; + name_list **old_table = charcode_name_table; + charcode_name_table_size = n + 256; + charcode_name_table = new name_list *[charcode_name_table_size]; + if (old_table) { + memcpy(charcode_name_table, old_table, old_size*sizeof(name_list *)); + a_delete old_table; + } + for (size_t i = old_size; i < charcode_name_table_size; i++) + charcode_name_table[i] = NULL; + } + + for (; ptr; ptr = strtok(NULL, " \n\t")) + charcode_name_table[n] = new name_list(ptr, charcode_name_table[n]); } fclose(fp); return 1; diff --git a/src/utils/hpftodit/hpftodit.man b/src/utils/hpftodit/hpftodit.man index c069752b..b914db9e 100644 --- a/src/utils/hpftodit/hpftodit.man +++ b/src/utils/hpftodit/hpftodit.man @@ -1,3 +1,4 @@ +.tr ~ .ig Copyright (C) 1994-2000, 2001, 2003 Free Software Foundation, Inc. @@ -23,12 +24,16 @@ the original English. .el .TP "\\$1" .. .TH HPFTODIT @MAN1EXT@ "@MDATE@" "Groff Version @VERSION@" +.\" -------------------------------------------------------------------------- .SH NAME +.\" -------------------------------------------------------------------------- hpftodit \- create font description files for use with groff \-Tlj4 +.\" -------------------------------------------------------------------------- .SH SYNOPSIS +.\" -------------------------------------------------------------------------- .B hpftodit [ -.B \-sv +.B \-adqsv ] [ .BI \-i n @@ -39,33 +44,53 @@ hpftodit \- create font description files for use with groff \-Tlj4 .PP It is possible to have whitespace between the .B \-i -command line option and its parameter. +option and its parameter. +.\" -------------------------------------------------------------------------- .SH DESCRIPTION +.\" -------------------------------------------------------------------------- .B hpftodit -creates a font file for use with -.B -groff \-Tlj4\fR -from an HP tagged font metric file. +creates a font file for use with an HP LaserJet printer with +.BR "groff \-Tlj4" , +using data from an HP tagged font metric (TFM) file. .I tfm_file -is the name of the tagged font metric file for the font. +is the name of the tagged font metric file for the font; Intellifont and +TrueType TFM files are supported, but symbol set TFM files are not. .I map_file -is a file giving the groff names for characters in the font; -this file should consist of a sequence of lines of the form: +is a file giving the groff names for characters in the font; this file +should consist of a sequence of lines of the form: .IP .I -n c1 c2 \fR.\|.\|. +m u c1 c2 \fR.\|.\|. .LP where -.I n +.I m is a decimal integer giving the MSL number of the character, +.I u +is a hexadecimal integer giving the Unicode value of the character, and .IR c1 , .IR c2 ,.\|.\|. are the groff names of the character. +The values can be separated by any whitespace; the Unicode value must +use uppercase digits A\^\(en\^F, and must be without a leading `0x', `u', or +\&`U+'. +The name for a glyph without a groff name may be given as +.RI u XXXX +if the glyph corresponds to a Unicode value, or as an unnamed glyph +`\-\^\-\^\-'. +If the given Unicode value is in the Private Use Area +(0xE000\^\(en\^0xF8FF), the glyph is included as an unnamed glyph. +Refer to +.BR groff_diff (@MAN1EXT@) +for additional information about unnamed glyphs and how to access them. +.LP .I font is the name of the groff font file. The groff font file is written to -.IR font . +.IR font ; +if +.I font +is specified as `\-', the output is written to the standard output. .LP The .B \-s @@ -75,7 +100,7 @@ option should be given if the font is special if .B troff should search it whenever -a character is not found in the current font.) +a character is not found in the current font). If the font is special, it should be listed in the .B fonts @@ -93,28 +118,97 @@ a left italic correction and a subscript correction for each character (the significance of these parameters is explained in .BR groff_font (@MAN5EXT@)). +.LP +The metrics generated by +.B hpftodit +assume that the DESC file contains values of 1200 for res and 6350 for +unitwidth (or any combination (e.g., 2400 and 3175) for which +res~\(mu~unitwidth~=~7\|620\|000). +Although HP PCL 5 LaserJet printers support an internal resolution of +7200 units per inch, they use a 16-bit signed integer for cursor +positioning; if +.B devlj4 +is to support U.S. ledger paper (11\(sd~\(mu~17\(sd), the maximum usable +resolution is 32\|767~/~17, or 1927, units per inch, which rounds down to +1200 units per inch. +If the largest required paper size is less (e.g., 8.5\(sd~\(mu~11\(sd or +A5), a greater resolution (and lesser unitwidth) can be specified. +.\" -------------------------------------------------------------------------- .SH OPTIONS +.\" -------------------------------------------------------------------------- +.TP +.B \-a +Include characters in the TFM file that do not have groff names and are +not included in the map file. +A glyph with corresponding Unicode value is given the name +.RI u XXXX ; +a glyph without a Unicode value is included as an unnamed glyph +`\-\^\-\^\-'. +A glyph with a Unicode value in the Private Use Area (0xE000\^\(en\^0xF8FF) +also is included as an unnamed glyph. +This option has no effect on Unicode-named or unnamed glyphs that are +specified in the map file. +.IP +This option provides a simple means of adding Unicode-named and unnamed +glyphs to a font without including them in the map file, but it affords +little control over which glyphs are placed in a regular font and which +are placed in a special font. +Although the presence or absence of the +.B \-s +option has some effect on which glyphs are included, it isn't very +selective\(emmany glyphs are placed in both regular and special fonts. +.\" -------------------------------------------------------------------------- +.TP +.B \-d +Dump information about the TFM file to the standard output; this option +can be useful for ensuring that a TFM file is a proper match for a font, +and that the contents of the TFM file are suitable. +The information includes the values of important TFM tags, and a listing +(by MSL number for Intellifont TFM files or by Unicode value for +TrueType TFM files) of the glyphs included in the TFM file. +The unit of measure `DU' for some tags indicates design units; there are +8782 design units per em for Intellifont fonts, and 2048 design units +per em for TrueType fonts. +Note that the accessibility of a glyph depends on its inclusion in a +symbol set; some TFM files list many glyphs but only a few symbol sets. +.IP +With this option, +.I map_file +and +.I font +are not required, and are ignored if given. +.\" -------------------------------------------------------------------------- +.TP +.B \-q +Suppress warnings about characters in the map file that were not found +in the TFM file. +Warnings never are given for unnamed glyphs or by glyphs named by their +Unicode values. +This option is useful when sending the output of +.B hpftodit +to the standard output. +.\" -------------------------------------------------------------------------- .TP .B \-v Print the version number. +.\" -------------------------------------------------------------------------- .TP .B \-s The font is special. -The effect of this option is to add the +This option adds the .B special -command to the font file. +command to the font file, and affects the HP symbol sets that are +searched for each glyph. +.\" -------------------------------------------------------------------------- .TP .BI \-i n -Generate an italic correction for each character so that -the character's width plus the character's italic correction -is equal to +Generate an italic correction for each character so that the character's +width plus the character's italic correction is equal to .I n -design units -plus the amount by which the right edge of the character's bounding -is to the right of the character's origin. -If this would result in a negative italic correction, use a zero -italic correction instead. -There are 8782 design units per em for Intellifont fonts. +thousandths of an em plus the amount by which the right edge of the character's +bounding is to the right of the character's origin. +If this would result in a negative italic correction, use a zero italic +correction instead. .IP Also generate a subscript correction equal to the product of the tangent of the slant of the font and @@ -126,13 +220,15 @@ instead. Also generate a left italic correction for each character equal to .I n -design units -plus the amount by which the left edge of the character's bounding box -is to the left of the character's origin. +thousandths of an em plus the amount by which the left edge of the +character's bounding box is to the left of the character's origin. The left italic correction may be negative. .IP -This option is normally needed only with italic (or oblique) fonts. +This option normally is needed only with italic or oblique fonts; +a value of 50 (0.05 em) usually is a reasonable choice. +.\" -------------------------------------------------------------------------- .SH FILES +.\" -------------------------------------------------------------------------- .Tp \w'\fB@FONTDIR@/devlj4/DESC'u+2n .B @FONTDIR@/devlj4/DESC Device description file. @@ -140,17 +236,53 @@ Device description file. .BI @FONTDIR@/devlj4/ F Font description file for font .IR F . -.SH BUGS +.\" -------------------------------------------------------------------------- +.SH LIMITATIONS +.\" -------------------------------------------------------------------------- +Although +.B hpftodit +can read TrueType TFM files, most of the HP-supplied TFM files for +TrueType fonts support relatively few glyphs and include little, if any, +kerning information. +When the HP LaserJet 4 printer was first introduced, most of the +internal scalable fonts were Agfa Intellifont. +The TFM files provided for these fonts supported 600+ glyphs and +contained extensive lists of kern pairs. +.LP +All scalable internal fonts on LaserJet printers introduced since +approximately 1996 have been TrueType. +With most developers using other means of obtaining font metrics by that +time, support for new TFM files was very limited. +The TFM files provided for the TrueType fonts support only the Latin 2 +(ISO 8859-2) symbol set, and include no kerning information; +consequently, they are of little value for any but the most rudimentary +documents. .LP -This program was written without the benefit of complete, official -documentation on the tagged font metric format. -It is therefore likely that it will fail to work on tfm files that are -dissimilar to those for the internal fonts on the Laserjet 4, -with which it was tested. +Because the Intellifont TFM files contain considerably more information, +they generally are preferable to the TrueType TFM files even for the +TrueType fonts in the newer printers. +The metrics for the TrueType fonts are very close, though not identical, +to those for the earlier Intellifont fonts of the same names. +Although most output using the Intellifont metrics with the newer +printers is quite acceptable, a few glyphs may fail to print as expected. .LP -TrueType tfm files are not supported. +At the time HP last supported TFM files, only Version 1 of the Unicode +standard was available. +Consequently, many glyphs lacking assigned code points were assigned by +HP to the Private Use Area (PUA). +Later versions of the Unicode standard included code points outside the +PUA for many of these glyphs. +The HP-supplied TrueType TFM files use the PUA assignments; +TFM files generated from more recent TrueType font files require the +later Unicode values to access the same glyphs. +Consequently, two different mapping files may be required: one for the +HP-supplied TFM files, and one for more recent TFM files. +.\" -------------------------------------------------------------------------- .SH "SEE ALSO" +.\" -------------------------------------------------------------------------- +.ad 0 .BR groff (@MAN1EXT@), +.BR groff_diff (@MAN1EXT@), .BR grolj4 (@MAN1EXT@), .BR groff_font (@MAN5EXT@) . diff --git a/src/utils/hpftodit/hpuni.cpp b/src/utils/hpftodit/hpuni.cpp new file mode 100644 index 00000000..892843ac --- /dev/null +++ b/src/utils/hpftodit/hpuni.cpp @@ -0,0 +1,698 @@ +// -*- C++ -*- +/* Copyright (C) 2003 Free Software Foundation, Inc. + Written by Jeff Conrad (jeff_conrad@msn.com) + +This file is part of groff. + +groff is free software; you can redistribute it and/or modify it under +the terms of the GNU General Public License as published by the Free +Software Foundation; either version 2, or (at your option) any later +version. + +groff is distributed in the hope that it will be useful, but WITHOUT ANY +WARRANTY; without even the implied warranty of MERCHANTABILITY or +FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +for more details. + +You should have received a copy of the GNU General Public License along +with groff; see the file COPYING. If not, write to the Free Software +Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ + +#include "lib.h" +#include "stringclass.h" +#include "ptable.h" + +#include "unicode.h" + +struct hp_msl_to_unicode { + char *value; +}; + +declare_ptable(hp_msl_to_unicode) +implement_ptable(hp_msl_to_unicode) + +PTABLE(hp_msl_to_unicode) hp_msl_to_unicode_table; + +struct { + const char *key; + const char *value; +} hp_msl_to_unicode_list[] = { + { "1", "0021", }, // Exclamation Mark + { "2", "0022", }, // Neutral Double Quote + { "3", "0023", }, // Number Sign + { "4", "0024", }, // Dollar Sign + { "5", "0025", }, // Per Cent Sign + { "6", "0026", }, // Ampersand + { "8", "2019", }, // Single Close Quote (9) + { "9", "0028", }, // Left Parenthesis + { "10", "0029", }, // Right Parenthesis + { "11", "002A", }, // Asterisk + { "12", "002B", }, // Plus Sign + { "13", "002C", }, // Comma, or Decimal Separator + { "14", "002D", }, // Hyphen + { "15", "002E", }, // Period, or Full Stop + { "16", "002F", }, // Solidus, or Slash + { "17", "0030", }, // Numeral Zero + { "18", "0031", }, // Numeral One + { "19", "0032", }, // Numeral Two + { "20", "0033", }, // Numeral Three + { "21", "0034", }, // Numeral Four + { "22", "0035", }, // Numeral Five + { "23", "0036", }, // Numeral Six + { "24", "0037", }, // Numeral Seven + { "25", "0038", }, // Numeral Eight + { "26", "0039", }, // Numeral Nine + { "27", "003A", }, // Colon + { "28", "003B", }, // Semicolon + { "29", "003C", }, // Less Than Sign + { "30", "003D", }, // Equals Sign + { "31", "003E", }, // Greater Than Sign + { "32", "003F", }, // Question Mark + { "33", "0040", }, // Commercial At + { "34", "0041", }, // Uppercase A + { "35", "0042", }, // Uppercase B + { "36", "0043", }, // Uppercase C + { "37", "0044", }, // Uppercase D + { "38", "0045", }, // Uppercase E + { "39", "0046", }, // Uppercase F + { "40", "0047", }, // Uppercase G + { "41", "0048", }, // Uppercase H + { "42", "0049", }, // Uppercase I + { "43", "004A", }, // Uppercase J + { "44", "004B", }, // Uppercase K + { "45", "004C", }, // Uppercase L + { "46", "004D", }, // Uppercase M + { "47", "004E", }, // Uppercase N + { "48", "004F", }, // Uppercase O + { "49", "0050", }, // Uppercase P + { "50", "0051", }, // Uppercase Q + { "51", "0052", }, // Uppercase R + { "52", "0053", }, // Uppercase S + { "53", "0054", }, // Uppercase T + { "54", "0055", }, // Uppercase U + { "55", "0056", }, // Uppercase V + { "56", "0057", }, // Uppercase W + { "57", "0058", }, // Uppercase X + { "58", "0059", }, // Uppercase Y + { "59", "005A", }, // Uppercase Z + { "60", "005B", }, // Left Bracket + { "61", "005C", }, // Reverse Solidus, or Backslash + { "62", "005D", }, // Right Bracket + { "63", "005E", }, // Circumflex, Exponent, or Pointer + { "64", "005F", }, // Underline or Underscore Character + { "66", "2018", }, // Single Open Quote (6) + { "67", "0061", }, // Lowercase A + { "68", "0062", }, // Lowercase B + { "69", "0063", }, // Lowercase C + { "70", "0064", }, // Lowercase D + { "71", "0065", }, // Lowercase E + { "72", "0066", }, // Lowercase F + { "73", "0067", }, // Lowercase G + { "74", "0068", }, // Lowercase H + { "75", "0069", }, // Lowercase I + { "76", "006A", }, // Lowercase J + { "77", "006B", }, // Lowercase K + { "78", "006C", }, // Lowercase L + { "79", "006D", }, // Lowercase M + { "80", "006E", }, // Lowercase N + { "81", "006F", }, // Lowercase O + { "82", "0070", }, // Lowercase P + { "83", "0071", }, // Lowercase Q + { "84", "0072", }, // Lowercase R + { "85", "0073", }, // Lowercase S + { "86", "0074", }, // Lowercase T + { "87", "0075", }, // Lowercase U + { "88", "0076", }, // Lowercase V + { "89", "0077", }, // Lowercase W + { "90", "0078", }, // Lowercase X + { "91", "0079", }, // Lowercase Y + { "92", "007A", }, // Lowercase Z + { "93", "007B", }, // Left Brace + { "94", "007C", }, // Long Vertical Mark + { "95", "007D", }, // Right Brace + { "96", "007E", }, // One Wavy Line Approximate + { "97", "2592", }, // Medium Shading Character + { "99", "00C0", }, // Uppercase A Grave + { "100", "00C2", }, // Uppercase A Circumflex + { "101", "00C8", }, // Uppercase E Grave + { "102", "00CA", }, // Uppercase E Circumflex + { "103", "00CB", }, // Uppercase E Dieresis + { "104", "00CE", }, // Uppercase I Circumflex + { "105", "00CF", }, // Uppercase I Dieresis + { "106", "00B4", }, // Lowercase Acute Accent (Spacing) + { "107", "0060", }, // Lowercase Grave Accent (Spacing) + { "108", "02C6", }, // Lowercase Circumflex Accent (Spacing) + { "109", "00A8", }, // Lowercase Dieresis Accent (Spacing) + { "110", "02DC", }, // Lowercase Tilde Accent (Spacing) + { "111", "00D9", }, // Uppercase U Grave + { "112", "00DB", }, // Uppercase U Circumflex + { "113", "00AF", }, // Overline, or Overscore Character + { "114", "00DD", }, // Uppercase Y Acute + { "115", "00FD", }, // Lowercase Y Acute + { "116", "00B0", }, // Degree Sign + { "117", "00C7", }, // Uppercase C Cedilla + { "118", "00E7", }, // Lowercase C Cedilla + { "119", "00D1", }, // Uppercase N Tilde + { "120", "00F1", }, // Lowercase N Tilde + { "121", "00A1", }, // Inverted Exclamation + { "122", "00BF", }, // Inverted Question Mark + { "123", "00A4", }, // Currency Symbol + { "124", "00A3", }, // Pound Sterling Sign + { "125", "00A5", }, // Yen Sign + { "126", "00A7", }, // Section Mark + { "127", "0192", }, // Florin Sign + { "128", "00A2", }, // Cent Sign + { "129", "00E2", }, // Lowercase A Circumflex + { "130", "00EA", }, // Lowercase E Circumflex + { "131", "00F4", }, // Lowercase O Circumflex + { "132", "00FB", }, // Lowercase U Circumflex + { "133", "00E1", }, // Lowercase A Acute + { "134", "00E9", }, // Lowercase E Acute + { "135", "00F3", }, // Lowercase O Acute + { "136", "00FA", }, // Lowercase U Acute + { "137", "00E0", }, // Lowercase A Grave + { "138", "00E8", }, // Lowercase E Grave + { "139", "00F2", }, // Lowercase O Grave + { "140", "00F9", }, // Lowercase U Grave + { "141", "00E4", }, // Lowercase A Dieresis + { "142", "00EB", }, // Lowercase E Dieresis + { "143", "00F6", }, // Lowercase O Dieresis + { "144", "00FC", }, // Lowercase U Dieresis + { "145", "00C5", }, // Uppercase A Ring + { "146", "00EE", }, // Lowercase I Circumflex + { "147", "00D8", }, // Uppercase O Oblique + { "148", "00C6", }, // Uppercase AE Diphthong + { "149", "00E5", }, // Lowercase A Ring + { "150", "00ED", }, // Lowercase I Acute + { "151", "00F8", }, // Lowercase O Oblique + { "152", "00E6", }, // Lowercase AE Diphthong + { "153", "00C4", }, // Uppercase A Dieresis + { "154", "00EC", }, // Lowercase I Grave + { "155", "00D6", }, // Uppercase O Dieresis + { "156", "00DC", }, // Uppercase U Dieresis + { "157", "00C9", }, // Uppercase E Acute + { "158", "00EF", }, // Lowercase I Dieresis + { "159", "00DF", }, // Lowercase Es-zet Ligature + { "160", "00D4", }, // Uppercase O Circumflex + { "161", "00C1", }, // Uppercase A Acute + { "162", "00C3", }, // Uppercase A Tilde + { "163", "00E3", }, // Lowercase A Tilde + { "164", "00D0", }, // Uppercase Eth +//{ "164", "0110", }, // Uppercase D-Stroke + { "165", "00F0", }, // Lowercase Eth + { "166", "00CD", }, // Uppercase I Acute + { "167", "00CC", }, // Uppercase I Grave + { "168", "00D3", }, // Uppercase O Acute + { "169", "00D2", }, // Uppercase O Grave + { "170", "00D5", }, // Uppercase O Tilde + { "171", "00F5", }, // Lowercase O Tilde + { "172", "0160", }, // Uppercase S Hacek + { "173", "0161", }, // Lowercase S Hacek + { "174", "00DA", }, // Uppercase U Acute + { "175", "0178", }, // Uppercase Y Dieresis + { "176", "00FF", }, // Lowercase Y Dieresis + { "177", "00DE", }, // Uppercase Thorn + { "178", "00FE", }, // Lowercase Thorn + { "180", "00B5", }, // Lowercase Greek Mu, or Micro + { "181", "00B6", }, // Pilcrow, or Paragraph Sign + { "182", "00BE", }, // Vulgar Fraction 3/4 + { "183", "2212", }, // Minus Sign + { "184", "00BC", }, // Vulgar Fraction 1/4 + { "185", "00BD", }, // Vulgar Fraction 1/2 + { "186", "00AA", }, // Female Ordinal + { "187", "00BA", }, // Male Ordinal + { "188", "00AB", }, // Left Pointing Double Angle Quote + { "189", "25A0", }, // Medium Solid Square Box + { "190", "00BB", }, // Right Pointing Double Angle Quote + { "191", "00B1", }, // Plus Over Minus Sign + { "192", "00A6", }, // Broken Vertical Mark + { "193", "00A9", }, // Copyright Sign + { "194", "00AC", }, // Not Sign + { "195", "00AD", }, // Soft Hyphen + { "196", "00AE", }, // Registered Sign + { "197", "00B2", }, // Superior Numeral 2 + { "198", "00B3", }, // Superior Numeral 3 + { "199", "00B8", }, // Lowercase Cedilla (Spacing) + { "200", "00B9", }, // Superior Numeral 1 + { "201", "00D7", }, // Multiply Sign + { "202", "00F7", }, // Divide Sign + { "203", "263A", }, // Open Smiling Face + { "204", "263B", }, // Solid Smiling Face + { "205", "2665", }, // Solid Heart, Card Suit + { "206", "2666", }, // Solid Diamond, Card Suit + { "207", "2663", }, // Solid Club, Card Suit + { "208", "2660", }, // Solid Spade, Card Suit + { "209", "25CF", }, // Medium Solid Round Bullet + { "210", "25D8", }, // Large Solid square with White Dot + { "211", "EFFD", }, // Large Open Round Bullet + { "212", "25D9", }, // Large Solid square with White Circle + { "213", "2642", }, // Male Symbol + { "214", "2640", }, // Female Symbol + { "215", "266A", }, // Musical Note + { "216", "266B", }, // Pair Of Musical Notes + { "217", "263C", }, // Compass, or Eight Pointed Sun + { "218", "25BA", }, // Right Solid Arrowhead + { "219", "25C4", }, // Left Solid Arrowhead + { "220", "2195", }, // Up/Down Arrow + { "221", "203C", }, // Double Exclamation Mark + { "222", "25AC", }, // Thick Horizontal Mark + { "223", "21A8", }, // Up/Down Arrow Baseline + { "224", "2191", }, // Up Arrow + { "225", "2193", }, // Down Arrow + { "226", "2192", }, // Right Arrow + { "227", "2190", }, // Left Arrow + { "229", "2194", }, // Left/Right Arrow + { "230", "25B2", }, // Up Solid Arrowhead + { "231", "25BC", }, // Down Solid Arrowhead + { "232", "20A7", }, // Pesetas Sign + { "233", "2310", }, // Reversed Not Sign + { "234", "2591", }, // Light Shading Character + { "235", "2593", }, // Dark Shading Character + { "236", "2502", }, // Box Draw Line, Vert. 1 + { "237", "2524", }, // Box Draw Right Tee, Vert. 1 Horiz. 1 + { "238", "2561", }, // Box Draw Right Tee, Vert. 1 Horiz. 2 + { "239", "2562", }, // Box Draw Right Tee, Vert. 2 Horiz. 1 + { "240", "2556", }, // Box Draw Upper Right Corner, Vert. 2 Horiz. 1 + { "241", "2555", }, // Box Draw Upper Right Corner, Vert. 1 Horiz. 2 + { "242", "2563", }, // Box Draw Right Tee, Vert. 2 Horiz. 2 + { "243", "2551", }, // Box Draw Lines, Vert. 2 + { "244", "2557", }, // Box Draw Upper Right Corner, Vert. 2 Horiz. 2 + { "245", "255D", }, // Box Draw Lower Right Corner, Vert. 2 Horiz. 2 + { "246", "255C", }, // Box Draw Lower Right Corner, Vert. 2 Horiz. 1 + { "247", "255B", }, // Box Draw Lower Right Corner, Vert. 1 Horiz. 2 + { "248", "2510", }, // Box Draw Upper Right Corner, Vert. 1, Horiz. 1 + { "249", "2514", }, // Box Draw Lower Left Corner, Vert. 1, Horiz. 1 + { "250", "2534", }, // Box Draw Bottom Tee, Vert. 1 Horiz. 1 + { "251", "252C", }, // Box Draw Top Tee, Vert. 1 Horiz. 1 + { "252", "251C", }, // Box Draw Left Tee, Vert. 1 Horiz. 1 + { "253", "2500", }, // Box Draw Line, Horiz. 1 + { "254", "253C", }, // Box Draw Cross, Vert. 1 Horiz. 1 + { "255", "255E", }, // Box Draw Left Tee, Vert. 1 Horiz. 2 + { "256", "255F", }, // Box Draw Left Tee, Vert. 2 Horz. 1 + { "257", "255A", }, // Box Draw Lower Left Corner, Vert. 2 Horiz. 2 + { "258", "2554", }, // Box Draw Upper Left Corner, Vert. 2 Horiz. 2 + { "259", "2569", }, // Box Draw Bottom Tee, Vert. 2 Horiz. 2 + { "260", "2566", }, // Box Draw Top Tee, Vert. 2 Horiz. 2 + { "261", "2560", }, // Box Draw Left Tee, Vert. 2 Horiz. 2 + { "262", "2550", }, // Box Draw Lines, Horiz. 2 + { "263", "256C", }, // Box Draw Cross Open Center, Vert. 2 Horiz. 2 + { "264", "2567", }, // Box Draw Bottom Tee, Vert. 1 Horiz. 2 + { "265", "2568", }, // Box Draw Bottom Tee, Vert. 2 Horiz. 1 + { "266", "2564", }, // Box Draw Top Tee, Vert. 1 Horiz. 2 + { "267", "2565", }, // Box Draw Top Tee, Vert. 2 Horiz. 1 + { "268", "2559", }, // Box Draw Lower Left Corner, Vert. 2 Horiz. 1 + { "269", "2558", }, // Box Draw Lower Left Corner, Vert. 1 Horiz. 2 + { "270", "2552", }, // Box Draw Upper Left Corner, Vert. 1 Horiz. 2 + { "271", "2553", }, // Box Draw Upper Left Corner, Vert. 2 Horiz. 1 + { "272", "256B", }, // Box Draw Cross, Vert. 2 Horiz. 1 + { "273", "256A", }, // Box Draw Cross, Vert. 1 Horiz. 2 + { "274", "2518", }, // Box Draw Lower Right Corner, Vert. 1 Horiz. 1 + { "275", "250C", }, // Box Draw Upper Left Corner, Vert. 1, Horiz. 1 + { "276", "2588", }, // Solid Full High/Wide + { "277", "2584", }, // Bottom Half Solid Rectangle + { "278", "258C", }, // Left Half Solid Rectangle + { "279", "2590", }, // Right Half Solid Rectangle + { "280", "2580", }, // Top Half Solid Rectangle + { "290", "2126", }, // Uppercase Greek Omega, or Ohms + { "292", "221E", }, // Infinity Symbol + { "295", "2229", }, // Set Intersection Symbol + { "296", "2261", }, // Exactly Equals Sign + { "297", "2265", }, // Greater Than or Equal Sign + { "298", "2264", }, // Less Than or Equal Sign + { "299", "2320", }, // Top Integral + { "300", "2321", }, // Bottom Integral + { "301", "2248", }, // Two Wavy Line Approximate Sign +//{ "302", "00B7", }, // Middle Dot, or Centered Period (see 2219) +//{ "302", "2219", }, // Centered Period, Middle Dot + { "302", "2219", }, // Math Dot, Centered Period + { "303", "221A", }, // Radical Symbol, Standalone Diagonal + { "305", "25AA", }, // Small Solid Square Box + { "306", "013F", }, // Uppercase L-Dot + { "307", "0140", }, // Lowercase L-Dot + { "308", "2113", }, // Litre Symbol + { "309", "0149", }, // Lowercase Apostrophe-N + { "310", "2032", }, // Prime, Minutes, or Feet Symbol + { "311", "2033", }, // Double Prime, Seconds, or Inches Symbol + { "312", "2020", }, // Dagger Symbol + { "313", "2122", }, // Trademark Sign + { "314", "2017", }, // Double Underline Character + { "315", "02C7", }, // Lowercase Hacek Accent (Spacing) + { "316", "02DA", }, // Lowercase Ring Accent (Spacing) + { "317", "EFF9", }, // Uppercase Acute Accent (Spacing) + { "318", "EFF8", }, // Uppercase Grave Accent (Spacing) + { "319", "EFF7", }, // Uppercase Circumflex Accent (Spacing) + { "320", "EFF6", }, // Uppercase Dieresis Accent (Spacing) + { "321", "EFF5", }, // Uppercase Tilde Accent (Spacing) + { "322", "EFF4", }, // Uppercase Hacek Accent (Spacing) + { "323", "EFF3", }, // Uppercase Ring Accent (Spacing) + { "324", "2215", }, // Vulgar Fraction Bar + { "325", "2014", }, // Em Dash + { "326", "2013", }, // En Dash + { "327", "2021", }, // Double Dagger Symbol + { "328", "0131", }, // Lowercase Undotted I + { "329", "0027", }, // Neutral Single Quote + { "330", "EFF2", }, // Uppercase Cedilla (Spacing) + { "331", "2022", }, // Small Solid Round Bullet + { "332", "207F", }, // Superior Lowercase N + { "333", "2302", }, // Home Plate + { "335", "0138", }, // Lowercase Kra + { "338", "0166", }, // Uppercase T-Stroke + { "339", "0167", }, // Lowercase T-Stroke + { "340", "014A", }, // Uppercase Eng + { "341", "014B", }, // Lowercase Eng + { "342", "0111", }, // Lowercase D-Stroke + { "400", "0102", }, // Uppercase A Breve + { "401", "0103", }, // Lowercase A Breve + { "402", "0100", }, // Uppercase A Macron + { "403", "0101", }, // Lowercase A Macron + { "404", "0104", }, // Uppercase A Ogonek + { "405", "0105", }, // Lowercase A Ogonek + { "406", "0106", }, // Uppercase C Acute + { "407", "0107", }, // Lowercase C Acute + { "410", "010C", }, // Uppercase C Hacek + { "411", "010D", }, // Lowercase C Hacek + { "414", "010E", }, // Uppercase D Hacek + { "415", "010F", }, // Lowercase D Hacek + { "416", "011A", }, // Uppercase E Hacek + { "417", "011B", }, // Lowercase E Hacek + { "418", "0116", }, // Uppercase E Overdot + { "419", "0117", }, // Lowercase E Overdot + { "420", "0112", }, // Uppercase E Macron + { "421", "0113", }, // Lowercase E Macron + { "422", "0118", }, // Uppercase E Ogonek + { "423", "0119", }, // Lowercase E Ogonek + { "428", "0122", }, // Uppercase G Cedilla + { "429", "0123", }, // Lowercase G Cedilla + { "432", "012E", }, // Uppercase I Ogonek + { "433", "012F", }, // Lowercase I Ogonek + { "434", "012A", }, // Uppercase I Macron + { "435", "012B", }, // Lowercase I Macron + { "438", "0136", }, // Uppercase K Cedilla + { "439", "0137", }, // Lowercase K Cedilla + { "440", "0139", }, // Uppercase L Acute + { "441", "013A", }, // Lowercase L Acute + { "442", "013D", }, // Uppercase L Hacek + { "443", "013E", }, // Lowercase L Hacek + { "444", "013B", }, // Uppercase L Cedilla + { "445", "013C", }, // Lowercase L Cedilla + { "446", "0143", }, // Uppercase N Acute + { "447", "0144", }, // Lowercase N Acute + { "448", "0147", }, // Uppercase N Hacek + { "449", "0148", }, // Lowercase N Hacek + { "450", "0145", }, // Uppercase N Cedilla + { "451", "0146", }, // Lowercase N Cedilla + { "452", "0150", }, // Uppercase O Double Acute + { "453", "0151", }, // Lowercase O Double Acute + { "454", "014C", }, // Uppercase O Macron + { "455", "014D", }, // Lowercase O Macron + { "456", "0154", }, // Uppercase R Acute + { "457", "0155", }, // Lowercase R Acute + { "458", "0158", }, // Uppercase R Hacek + { "459", "0159", }, // Lowercase R Hacek + { "460", "0156", }, // Uppercase R Cedilla + { "461", "0157", }, // Lowercase R Cedilla + { "462", "015A", }, // Uppercase S Acute + { "463", "015B", }, // Lowercase S Acute + { "466", "0164", }, // Uppercase T Hacek + { "467", "0165", }, // Lowercase T Hacek + { "468", "0162", }, // Uppercase T Cedilla + { "469", "0163", }, // Lowercase T Cedilla + { "470", "0168", }, // Uppercase U Tilde + { "471", "0169", }, // Lowercase U Tilde + { "474", "0170", }, // Uppercase U Double Acute + { "475", "0171", }, // Lowercase U Double Acute + { "476", "016E", }, // Uppercase U Ring + { "477", "016F", }, // Lowercase U Ring + { "478", "016A", }, // Uppercase U Macron + { "479", "016B", }, // Lowercase U Macron + { "480", "0172", }, // Uppercase U Ogonek + { "481", "0173", }, // Lowercase U Ogonek + { "482", "0179", }, // Uppercase Z Acute + { "483", "017A", }, // Lowercase Z Acute + { "484", "017B", }, // Uppercase Z Overdot + { "485", "017C", }, // Lowercase Z Overdot + { "486", "0128", }, // Uppercase I Tilde + { "487", "0129", }, // Lowercase I Tilde + { "500", "EFBF", }, // Radical, Diagonal, Composite + { "501", "221D", }, // Proportional To Symbol + { "502", "212F", }, // Napierian (italic e) + { "503", "03F5", }, // Alternate Lowercase Greek Epsilon +//{ "503", "EFEC", }, // Alternate Lowercase Greek Epsilon + { "504", "2234", }, // Therefore Symbol + { "505", "0393", }, // Uppercase Greek Gamma + { "506", "2206", }, // Increment Symbol (Delta) + { "507", "0398", }, // Uppercase Greek Theta + { "508", "039B", }, // Uppercase Greek Lambda + { "509", "039E", }, // Uppercase Greek Xi + { "510", "03A0", }, // Uppercase Greek Pi + { "511", "03A3", }, // Uppercase Greek Sigma + { "512", "03A5", }, // Uppercase Greek Upsilon + { "513", "03A6", }, // Uppercase Greek Phi + { "514", "03A8", }, // Uppercase Greek Psi + { "515", "03A9", }, // Uppercase Greek Omega + { "516", "2207", }, // Nabla Symbol (inverted Delta) + { "517", "2202", }, // Partial Differential Delta Symbol + { "518", "03C2", }, // Lowercase Sigma, Terminal + { "519", "2260", }, // Not Equal To Symbol + { "520", "EFEB", }, // Underline, Composite + { "521", "2235", }, // Because Symbol + { "522", "03B1", }, // Lowercase Greek Alpha + { "523", "03B2", }, // Lowercase Greek Beta + { "524", "03B3", }, // Lowercase Greek Gamma + { "525", "03B4", }, // Lowercase Greek Delta + { "526", "03B5", }, // Lowercase Greek Epsilon + { "527", "03B6", }, // Lowercase Greek Zeta + { "528", "03B7", }, // Lowercase Greek Eta + { "529", "03B8", }, // Lowercase Greek Theta + { "530", "03B9", }, // Lowercase Greek Iota + { "531", "03BA", }, // Lowercase Greek Kappa + { "532", "03BB", }, // Lowercase Greek Lambda + { "533", "03BC", }, // Lowercase Greek Mu + { "534", "03BD", }, // Lowercase Greek Nu + { "535", "03BE", }, // Lowercase Greek Xi + { "536", "03BF", }, // Lowercase Greek Omicron + { "537", "03C0", }, // Lowercase Greek Pi + { "538", "03C1", }, // Lowercase Greek Rho + { "539", "03C3", }, // Lowercase Greek Sigma + { "540", "03C4", }, // Lowercase Greek Tau + { "541", "03C5", }, // Lowercase Greek Upsilon + { "542", "03C6", }, // Lowercase Greek Phi + { "543", "03C7", }, // Lowercase Greek Chi + { "544", "03C8", }, // Lowercase Greek Psi + { "545", "03C9", }, // Lowercase Greek Omega + { "546", "03D1", }, // Lowercase Greek Theta, Open + { "547", "03D5", }, // Lowercase Greek Phi, Open + { "548", "03D6", }, // Lowercase Pi, Alternate + { "549", "2243", }, // Wavy Over Straight Approximate Symbol + { "550", "2262", }, // Not Exactly Equal To Symbol + { "551", "21D1", }, // Up Arrow Double Stroke + { "552", "21D2", }, // Right Arrow Double Stroke + { "553", "21D3", }, // Down Arrow Double Stroke + { "554", "21D0", }, // Left Arrow Double Stroke + { "555", "21D5", }, // Up/Down Arrow Double Stroke + { "556", "21D4", }, // Left/Right Arrow Double Stroke + { "557", "21C4", }, // Right Over Left Arrow + { "558", "21C6", }, // Left Over Right Arrow + { "559", "EFE9", }, // Vector Symbol + { "560", "0305", }, // Overline, Composite + { "561", "2200", }, // For All Symbol, or Universal (inverted A) + { "562", "2203", }, // There Exists Symbol, or Existential (inverted E) + { "563", "22A4", }, // Top Symbol + { "564", "22A5", }, // Bottom Symbol + { "565", "222A", }, // Set Union Symbol + { "566", "2208", }, // Element-Of Symbol + { "567", "220B", }, // Contains Symbol + { "568", "2209", }, // Not-Element-Of Symbol + { "569", "2282", }, // Proper Subset Symbol + { "570", "2283", }, // Proper Superset Symbol + { "571", "2284", }, // Not Proper Subset Symbol + { "572", "2285", }, // Not Proper Superset Symbol + { "573", "2286", }, // Subset Symbol + { "574", "2287", }, // Superset Symbol + { "575", "2295", }, // Plus In Circle Symbol + { "576", "2299", }, // Dot In Circle Symbol + { "577", "2297", }, // Times In Circle Symbol + { "578", "2296", }, // Minus In Circle Symbol + { "579", "2298", }, // Slash In Circle Symbol + { "580", "2227", }, // Logical And Symbol + { "581", "2228", }, // Logical Or Symbol + { "582", "22BB", }, // Exclusive Or Symbol + { "583", "2218", }, // Functional Composition Symbol + { "584", "20DD", }, // Large Open Circle + { "585", "22A3", }, // Assertion Symbol + { "586", "22A2", }, // Backwards Assertion Symbol + { "587", "222B", }, // Integral Symbol + { "588", "222E", }, // Curvilinear Integral Symbol + { "589", "2220", }, // Angle Symbol + { "590", "2205", }, // Empty Set Symbol + { "591", "2135", }, // Hebrew Aleph + { "592", "2136", }, // Hebrew Beth + { "593", "2137", }, // Hebrew Gimmel + { "594", "212D", }, // Fraktur Uppercase C + { "595", "2111", }, // Fraktur Uppercase I + { "596", "211C", }, // Fraktur Uppercase R + { "597", "2128", }, // Fraktur Uppercase Z + { "598", "23A1", }, // Top Segment Left Bracket (Left Square Bracket Upper Corner) + { "599", "23A3", }, // Bottom Segment Left Bracket (Left Square Bracket Lower Corner) + { "600", "239B", }, // Top Segment Left Brace (Left Parenthesis Upper Hook) +//{ "600", "23A7", }, // Top Segment Left Brace (Right Curly Bracket Upper Hook) + { "601", "23A8", }, // Middle Segment Left Brace (Right Curly Bracket Middle Piece) + { "602", "239D", }, // Bottom Segment LeftBrace (Left Parenthesis Lower Hook) +//{ "602", "23A9", }, // Bottom Segment Left Brace (Right Curly Bracket Lower Hook) + { "603", "EFD4", }, // Middle Segment Curvilinear Integral + { "604", "EFD3", }, // Top Left Segment Summation + { "605", "2225", }, // Double Vertical Line, Composite + { "606", "EFD2", }, // Bottom Left Segment Summation + { "607", "EFD1", }, // Bottom Diagonal Summation + { "608", "23A4", }, // Top Segment Right Bracket (Right Square Bracket Upper Corner) + { "609", "23A6", }, // Bottom Segment Right Bracket (Right Square Bracket Lower Corner) + { "610", "239E", }, // Top Segment Right Brace (Right Parenthesis Upper Hook) +//{ "610", "23AB", }, // Top Segment Right Brace (Right Curly Bracket Upper Hook) + { "611", "23AC", }, // Middle Segment Right Brace (Right Curly Bracket Middle Piece) + { "612", "23A0", }, // Bottom Segment Right ( Right Parenthesis Lower Hook) +//{ "612", "23AD", }, // Bottom Segment Right Brace (Right Curly Bracket Lower Hook) + { "613", "239C", }, // Thick Vertical Line, Composite (Left Parenthesis Extension) +//{ "613", "239F", }, // Thick Vertical Line, Composite (Right Parenthesis Extension) +//{ "613", "23AA", }, // Thick Vertical Line, Composite (Curly Bracket Extension) +//{ "613", "23AE", }, // Thick Vertical Line, Composite (Integral Extension) + { "614", "2223", }, // Thin Vertical Line, Composite + { "615", "EFDC", }, // Bottom Segment of Vertical Radical + { "616", "EFD0", }, // Top Right Segment Summation + { "617", "EFCF", }, // Middle Segment Summation + { "618", "EFCE", }, // Bottom Right Segment Summation + { "619", "EFCD", }, // Top Diagonal Summation + { "620", "2213", }, // Minus Over Plus Sign + { "621", "2329", }, // Left Angle Bracket + { "622", "232A", }, // Right Angle Bracket + { "623", "EFFF", }, // Mask Symbol + { "624", "2245", }, // Wavy Over Two Straight Approximate Symbol + { "625", "2197", }, // 45 Degree Arrow + { "626", "2198", }, // -45 Degree Arrow + { "627", "2199", }, // -135 Degree Arrow + { "628", "2196", }, // 135 Degree Arrow + { "629", "25B5", }, // Up Open Triangle + { "630", "25B9", }, // Right Open Triangle + { "631", "25BF", }, // Down Open Triangle + { "632", "25C3", }, // Left Open Triangle + { "633", "226A", }, // Much Less Than Sign + { "634", "226B", }, // Much Greater Than Sign + { "635", "2237", }, // Proportional To Symbol (4 dots) + { "636", "225C", }, // Defined As Symbol + { "637", "03DD", }, // Lowercase Greek Digamma + { "638", "210F", }, // Planck's Constant divided by 2 pi + { "639", "2112", }, // Laplace Transform Symbol + { "640", "EFFE", }, // Power Set + { "641", "2118", }, // Weierstrassian Symbol + { "642", "2211", }, // Summation Symbol (large Sigma) + { "643", "301A", }, // Left Double Bracket + { "644", "EFC9", }, // Middle Segment Double Bracket + { "645", "301B", }, // Right Double Bracket + { "646", "256D", }, // Box Draw Left Top Round Corner + { "647", "2570", }, // Box Draw Left Bottom Round Corner + { "648", "EFC8", }, // Extender Large Union/Product + { "649", "EFC7", }, // Bottom Segment Large Union + { "650", "EFC6", }, // Top Segment Large Intersection + { "651", "EFC5", }, // Top Segment Left Double Bracket + { "652", "EFC4", }, // Bottom Segment Left Double Bracket + { "653", "EFFC", }, // Large Open Square Box + { "654", "25C7", }, // Open Diamond + { "655", "256E", }, // Box Draw Right Top Round Corner + { "656", "256F", }, // Box Draw Right Bottom Round Corner + { "657", "EFC3", }, // Bottom Segment Large Bottom Product + { "658", "EFC2", }, // Top Segment Large Top Product + { "659", "EFC1", }, // Top Segment Right Double Bracket + { "660", "EFC0", }, // Bottom Segment Right Double Bracket + { "661", "EFFB", }, // Large Solid Square Box + { "662", "25C6", }, // Solid Diamond + { "663", "220D", }, // Such That Symbol (rotated lc epsilon) + { "664", "2217", }, // Math Asterisk + { "665", "23AF", }, // Horizontal Arrow Extender (Horizontal Line Extension) + { "666", "EFCB", }, // Double Horizontal Arrow Extender + { "667", "EFCC", }, // Inverted Complement of 0xEFCF or MSL 617 + { "668", "221F", }, // Right Angle Symbol + { "669", "220F", }, // Product Symbol (large Pi) + { "684", "25CA", }, // Lozenge, Diamond + { "1000", "2070", }, // Superior Numeral 0 + { "1001", "2074", }, // Superior Numeral 4 + { "1002", "2075", }, // Superior Numeral 5 + { "1003", "2076", }, // Superior Numeral 6 + { "1004", "2077", }, // Superior Numeral 7 + { "1005", "2078", }, // Superior Numeral 8 + { "1006", "2079", }, // Superior Numeral 9 + { "1017", "201C", }, // Double Open Quote (6) + { "1018", "201D", }, // Double Close Quote (9) + { "1019", "201E", }, // Double Baseline Quote (9) + { "1020", "2003", }, // Em Space + { "1021", "2002", }, // En Space + { "1023", "2009", }, // Thin Space + { "1028", "2026", }, // Ellipsis + { "1030", "EFF1", }, // Uppercase Ogonek (Spacing) + { "1031", "017E", }, // Lowercase Z Hacek + { "1034", "2120", }, // Service Mark + { "1036", "211E", }, // Prescription Sign +//{ "1040", "F001", }, // Lowercase FI Ligature + { "1040", "FB01", }, // Lowercase FI Ligature +//{ "1041", "F002", }, // Lowercase FL Ligature + { "1041", "FB02", }, // Lowercase FL Ligature + { "1042", "FB00", }, // Lowercase FF Ligature + { "1043", "FB03", }, // Lowercase FFI Ligature + { "1044", "FB04", }, // Lowercase FFL Ligature + { "1045", "EFF0", }, // Uppercase Double Acute Accent (Spacing) + { "1047", "0133", }, // Lowercase IJ Ligature + { "1060", "2105", }, // Care Of Symbol + { "1061", "011E", }, // Uppercase G Breve + { "1062", "011F", }, // Lowercase G Breve + { "1063", "015E", }, // Uppercase S Cedilla + { "1064", "015F", }, // Lowercase S Cedilla + { "1065", "0130", }, // Uppercase I Overdot + { "1067", "201A", }, // Single Baseline Quote (9) + { "1068", "2030", }, // Per Mill Sign + { "1069", "20AC", }, // Euro + { "1084", "02C9", }, // Lowercase Macron Accent (Spacing) + { "1086", "02D8", }, // Lowercase Breve Accent (Spacing) + { "1088", "02D9", }, // Lowercase Overdot Accent (Spacing) + { "1090", "0153", }, // Lowercase OE Ligature + { "1091", "0152", }, // Uppercase OE Ligature + { "1092", "2039", }, // Left Pointing Single Angle Quote + { "1093", "203A", }, // Right Pointing Single Angle Quote + { "1094", "25A1", }, // Medium Open Square Box + { "1095", "0141", }, // Uppercase L-Stroke + { "1096", "0142", }, // Lowercase L-Stroke + { "1097", "02DD", }, // Lowercase Double Acute Accent (Spacing) + { "1098", "02DB", }, // Lowercase Ogonek (Spacing) + { "1099", "21B5", }, // Carriage Return Symbol + { "1100", "EFDB", }, // Full Size Serif Registered + { "1101", "EFDA", }, // Full Size Serif Copyright + { "1102", "EFD9", }, // Full Size Serif Trademark + { "1103", "EFD8", }, // Full Size Sans Registered + { "1104", "EFD7", }, // Full Size Sans Copyright + { "1105", "EFD6", }, // Full Size Sans Trademark + { "1106", "017D", }, // Uppercase Z Hacek + { "1107", "0132", }, // Uppercase IJ Ligature + { "1108", "25AB", }, // Small Open Square Box + { "1109", "25E6", }, // Small Open Round Bullet + { "1110", "25CB", }, // Medium Open Round Bullet + { "1111", "EFFA", }, // Large Solid Round Bullet + { "3812", "F000", }, // Ornament, Apple +}; + +// global constructor +static struct hp_msl_to_unicode_init { + hp_msl_to_unicode_init(); +} _hp_msl_to_unicode_init; + +hp_msl_to_unicode_init::hp_msl_to_unicode_init() { + for (unsigned int i = 0; + i < sizeof(hp_msl_to_unicode_list)/sizeof(hp_msl_to_unicode_list[0]); + i++) { + hp_msl_to_unicode *ptu = new hp_msl_to_unicode[1]; + ptu->value = (char *)hp_msl_to_unicode_list[i].value; + hp_msl_to_unicode_table.define(hp_msl_to_unicode_list[i].key, ptu); + } +} + +const char *hp_msl_to_unicode_code(const char *s) +{ + hp_msl_to_unicode *result = hp_msl_to_unicode_table.lookup(s); + return result ? result->value : 0; +} |