|
1 # |
|
2 # Copyright (c) 1997-2009 Nokia Corporation and/or its subsidiary(-ies). |
|
3 # All rights reserved. |
|
4 # This component and the accompanying materials are made available |
|
5 # under the terms of "Eclipse Public License v1.0" |
|
6 # which accompanies this distribution, and is available |
|
7 # at the URL "http://www.eclipse.org/legal/epl-v10.html". |
|
8 # |
|
9 # Initial Contributors: |
|
10 # Nokia Corporation - initial contribution. |
|
11 # |
|
12 # Contributors: |
|
13 # |
|
14 # Description: |
|
15 # |
|
16 |
|
17 use strict; |
|
18 use integer; |
|
19 |
|
20 BEGIN |
|
21 { |
|
22 my $perlScriptPath=$0; |
|
23 my $os = $^O; #get the OS type |
|
24 #check OS type |
|
25 if($os=~/MSWin32/) #Windows OS |
|
26 { |
|
27 $perlScriptPath=~s/\//\\/g; # replace any forward-slashes with back-slashes |
|
28 $perlScriptPath=~s/(\\?)[^\\]+$/$1/; # get rid of this Perl-script's file-name |
|
29 } |
|
30 else #Unix OS |
|
31 { |
|
32 $perlScriptPath=~s/\\/\//g; # replace any back-slashes with forward-slashes |
|
33 $perlScriptPath=~s/(\/?)[^\/]+$/$1/; # get rid of this Perl-script's file-name |
|
34 } |
|
35 unshift(@INC, $perlScriptPath); # can't do "use lib $perlScriptPath" here as "use lib" only seems to work with *hard-coded* directory names |
|
36 } |
|
37 use PARSER; |
|
38 use WRITER; |
|
39 |
|
40 $|=1; # ensures that any progress information sent to the screen is displayed immediately and not buffered |
|
41 if ((@ARGV==0) || ($ARGV[0]=~/\?/i) || ($ARGV[0]=~/-h/i) || ($ARGV[0]=~/help/i)) |
|
42 { |
|
43 die("\nVersion 021\n\nCharacter-set conversion-table generating tool\nCopyright (c) 2000-2009 Nokia Corporation and/or its subsidiary(-ies).\n\nUsage:\n\n\tcnvtool <control-file> <source-file> <output-file> [options]\n\nwhere the following options are available (each has a short form and a long form which are shown below separated by a '|'):\n\n\t-s | -generateSourceCode\n\t-c | -columns(<a>: <b>, <c>)\n\t-r | -omitReplacementForUnconvertibleUnicodeCharacters\n\t-p | -cutOutAnyPrivateUseUnicodeCharacterSlotsBeingUsed\n\t-u | -sourceFilesToSubtract(<a>, <b>, ...)\n\n"); |
|
44 } |
|
45 my $generateSourceCode=0; |
|
46 my @columns=(2, 1, 2); |
|
47 my $omitReplacementForUnconvertibleUnicodeCharacters=0; |
|
48 my $cutOutAnyPrivateUseUnicodeCharacterSlotsBeingUsed=0; |
|
49 my @sourceFilesToSubtract=(); |
|
50 my $flattenHashAndSave=0; # this flag is not published for use outside of the CHARCONV component |
|
51 &extractCommandLineFlags(\$generateSourceCode, \@columns, \$omitReplacementForUnconvertibleUnicodeCharacters, \$cutOutAnyPrivateUseUnicodeCharacterSlotsBeingUsed, \@sourceFilesToSubtract, \$flattenHashAndSave); |
|
52 (!$omitReplacementForUnconvertibleUnicodeCharacters || $generateSourceCode) or die("Error: bad combination of flags\n"); |
|
53 my $controlFile=shift; |
|
54 my $sourceFile=shift; |
|
55 my $outputFile=shift; |
|
56 print("Generating $outputFile...\n"); |
|
57 my $uid=0; |
|
58 my $endiannessAsText=''; |
|
59 my $endianness=0; |
|
60 my $replacementForUnconvertibleUnicodeCharacters=''; |
|
61 my @foreignVariableByteData=(); |
|
62 my @foreignToUnicodeData=(); |
|
63 my @unicodeToForeignData=(); |
|
64 my %foreignCharacterCodes=(); |
|
65 my %unicodeCharacterCodes=(); |
|
66 my %preferredForeignCharacterCodesForConflictResolution=(); |
|
67 my %preferredUnicodeCharacterCodesForConflictResolution=(); |
|
68 my %additionalSubsetTables=(); |
|
69 my %privateUseUnicodeCharacterSlotsUsed=(); |
|
70 |
|
71 print(" reading $controlFile...\n"); |
|
72 open(CONTROL_FILE, "< $controlFile") or die("Error: could not open \"$controlFile\" for reading\n"); |
|
73 &readHeaderFromControlFile(\*CONTROL_FILE, $controlFile, $generateSourceCode, \$uid, \$endiannessAsText, \$endianness, \$replacementForUnconvertibleUnicodeCharacters, $flattenHashAndSave); |
|
74 &readForeignVariableByteDataFromControlFile(\*CONTROL_FILE, $controlFile, \@foreignVariableByteData); |
|
75 &readOneDirectionDataFromControlFile(\*CONTROL_FILE, $controlFile, \@foreignToUnicodeData, \%preferredUnicodeCharacterCodesForConflictResolution, \%additionalSubsetTables, 1); |
|
76 &readOneDirectionDataFromControlFile(\*CONTROL_FILE, $controlFile, \@unicodeToForeignData, \%preferredForeignCharacterCodesForConflictResolution, \%additionalSubsetTables, 0); |
|
77 close(CONTROL_FILE) or die("Error: could not close \"$controlFile\"\n"); |
|
78 |
|
79 print(" reading $sourceFile...\n"); |
|
80 open(SOURCE_FILE, "< $sourceFile") or die("Error: could not open \"$sourceFile\" for reading\n"); |
|
81 &readSourceFile(\*SOURCE_FILE, $sourceFile, \%foreignCharacterCodes, \%unicodeCharacterCodes, \@columns, $cutOutAnyPrivateUseUnicodeCharacterSlotsBeingUsed, \%privateUseUnicodeCharacterSlotsUsed, 0); |
|
82 close(SOURCE_FILE) or die("Error: could not close \"$sourceFile\"\n"); |
|
83 |
|
84 my $sourceFileToSubtract; |
|
85 foreach $sourceFileToSubtract (@sourceFilesToSubtract) |
|
86 { |
|
87 print(" subtracting from $sourceFileToSubtract...\n"); |
|
88 open(SOURCE_FILE_TO_SUBTRACT, "< $sourceFileToSubtract") or die("Error: could not open \"$sourceFileToSubtract\" for reading\n"); |
|
89 &readSourceFile(\*SOURCE_FILE_TO_SUBTRACT, $sourceFileToSubtract, \%foreignCharacterCodes, \%unicodeCharacterCodes, \@columns, $cutOutAnyPrivateUseUnicodeCharacterSlotsBeingUsed, \%privateUseUnicodeCharacterSlotsUsed, 1); |
|
90 close(SOURCE_FILE_TO_SUBTRACT) or die("Error: could not close \"$sourceFileToSubtract\"\n"); |
|
91 } |
|
92 |
|
93 &warnIfAnyPrivateUseUnicodeCharacterSlotsBeingUsed(\%privateUseUnicodeCharacterSlotsUsed); |
|
94 &resolveConflictsAndFlattenArraysToScalars(\%foreignCharacterCodes, \%preferredForeignCharacterCodesForConflictResolution, 'Unicode', 'foreign'); |
|
95 &resolveConflictsAndFlattenArraysToScalars(\%unicodeCharacterCodes, \%preferredUnicodeCharacterCodesForConflictResolution, 'foreign', 'Unicode'); |
|
96 &checkForeignVariableByteData($endianness, \@foreignVariableByteData, \@foreignToUnicodeData); |
|
97 |
|
98 print(" writing $outputFile...\n"); |
|
99 open(OUTPUT_FILE, "> $outputFile") or die("Error: could not open \"$outputFile\" for writing\n"); |
|
100 if ($generateSourceCode) |
|
101 { |
|
102 my @sourceCodeOfForeignToUnicodeIndexedTables16=(); |
|
103 my @sourceCodeOfForeignToUnicodeKeyedTables1616=(); |
|
104 my @sourceCodeOfForeignToUnicodeKeyedTables16OfIndexedTables16_indexedEntries=(); |
|
105 my @sourceCodeOfForeignToUnicodeKeyedTables16OfIndexedTables16_keyedEntries=(); |
|
106 |
|
107 my @sourceCodeOfUnicodeToForeignIndexedTables16=(); |
|
108 my @sourceCodeOfUnicodeToForeignKeyedTables1616=(); |
|
109 my @sourceCodeOfUnicodeToForeignKeyedTables16OfIndexedTables16_indexedEntries=(); |
|
110 my @sourceCodeOfUnicodeToForeignKeyedTables16OfIndexedTables16_keyedEntries=(); |
|
111 |
|
112 # new for 32 bit encoding begin |
|
113 my @sourceCodeOfForeignToUnicodeIndexedTables32=(); |
|
114 my @sourceCodeOfForeignToUnicodeKeyedTables3232=(); |
|
115 my @sourceCodeOfForeignToUnicodeKeyedTables32OfIndexedTables32_indexedEntries=(); |
|
116 my @sourceCodeOfForeignToUnicodeKeyedTables32OfIndexedTables32_keyedEntries=(); |
|
117 |
|
118 my @sourceCodeOfUnicodeToForeignIndexedTables32=(); |
|
119 my @sourceCodeOfUnicodeToForeignKeyedTables3232=(); |
|
120 my @sourceCodeOfUnicodeToForeignKeyedTables32OfIndexedTables32_indexedEntries=(); |
|
121 my @sourceCodeOfUnicodeToForeignKeyedTables32OfIndexedTables32_keyedEntries=(); |
|
122 # new for 32 bit endcoding end |
|
123 |
|
124 my @sourceCodeOfTopLevelStructures=(); |
|
125 |
|
126 &writeSourceCodeHeader(\*OUTPUT_FILE, $outputFile, $replacementForUnconvertibleUnicodeCharacters); |
|
127 &writeSourceCodeForeignVariableByteData(\@sourceCodeOfTopLevelStructures, \@foreignVariableByteData); |
|
128 &writeSourceCodeOneDirectionData(\@sourceCodeOfTopLevelStructures, |
|
129 \@sourceCodeOfForeignToUnicodeIndexedTables16, \@sourceCodeOfForeignToUnicodeKeyedTables1616, \@sourceCodeOfForeignToUnicodeKeyedTables16OfIndexedTables16_indexedEntries, \@sourceCodeOfForeignToUnicodeKeyedTables16OfIndexedTables16_keyedEntries, |
|
130 \@sourceCodeOfForeignToUnicodeIndexedTables32, \@sourceCodeOfForeignToUnicodeKeyedTables3232, \@sourceCodeOfForeignToUnicodeKeyedTables32OfIndexedTables32_indexedEntries, \@sourceCodeOfForeignToUnicodeKeyedTables32OfIndexedTables32_keyedEntries, |
|
131 \@foreignToUnicodeData, \%unicodeCharacterCodes, 1); |
|
132 &writeSourceCodeOneDirectionData(\@sourceCodeOfTopLevelStructures, |
|
133 \@sourceCodeOfUnicodeToForeignIndexedTables16, \@sourceCodeOfUnicodeToForeignKeyedTables1616, \@sourceCodeOfUnicodeToForeignKeyedTables16OfIndexedTables16_indexedEntries, \@sourceCodeOfUnicodeToForeignKeyedTables16OfIndexedTables16_keyedEntries, |
|
134 \@sourceCodeOfUnicodeToForeignIndexedTables32, \@sourceCodeOfUnicodeToForeignKeyedTables3232, \@sourceCodeOfUnicodeToForeignKeyedTables32OfIndexedTables32_indexedEntries, \@sourceCodeOfUnicodeToForeignKeyedTables32OfIndexedTables32_keyedEntries, |
|
135 \@unicodeToForeignData, \%foreignCharacterCodes, 0); |
|
136 &writeSourceCodeFinalStuff(\*OUTPUT_FILE, |
|
137 \@sourceCodeOfForeignToUnicodeIndexedTables16, \@sourceCodeOfForeignToUnicodeKeyedTables1616, \@sourceCodeOfForeignToUnicodeKeyedTables16OfIndexedTables16_indexedEntries, \@sourceCodeOfForeignToUnicodeKeyedTables16OfIndexedTables16_keyedEntries, |
|
138 \@sourceCodeOfUnicodeToForeignIndexedTables16, \@sourceCodeOfUnicodeToForeignKeyedTables1616, \@sourceCodeOfUnicodeToForeignKeyedTables16OfIndexedTables16_indexedEntries, \@sourceCodeOfUnicodeToForeignKeyedTables16OfIndexedTables16_keyedEntries, |
|
139 \@sourceCodeOfForeignToUnicodeIndexedTables32, \@sourceCodeOfForeignToUnicodeKeyedTables3232, \@sourceCodeOfForeignToUnicodeKeyedTables32OfIndexedTables32_indexedEntries, \@sourceCodeOfForeignToUnicodeKeyedTables32OfIndexedTables32_keyedEntries, |
|
140 \@sourceCodeOfUnicodeToForeignIndexedTables32, \@sourceCodeOfUnicodeToForeignKeyedTables3232, \@sourceCodeOfUnicodeToForeignKeyedTables32OfIndexedTables32_indexedEntries, \@sourceCodeOfUnicodeToForeignKeyedTables32OfIndexedTables32_keyedEntries, |
|
141 \@sourceCodeOfTopLevelStructures, $endiannessAsText, \%additionalSubsetTables); |
|
142 } |
|
143 elsif ($flattenHashAndSave) |
|
144 { |
|
145 binmode OUTPUT_FILE; |
|
146 #instead of calling the writeBinaryHeader, just write the data I need followed by |
|
147 # writeBinaryForeignVariableByteData... |
|
148 &write8(\*OUTPUT_FILE, $endianness); |
|
149 &write8(\*OUTPUT_FILE, length($replacementForUnconvertibleUnicodeCharacters)); |
|
150 &writeString(\*OUTPUT_FILE, $replacementForUnconvertibleUnicodeCharacters); |
|
151 &writeBinaryForeignVariableByteData(\*OUTPUT_FILE, \@foreignVariableByteData); |
|
152 #choose %unicodeCharacterCodes and write the data as keypair |
|
153 my $key; |
|
154 my $rangekey; |
|
155 my $limit; |
|
156 foreach $key (keys(%unicodeCharacterCodes)) |
|
157 { |
|
158 &write16(\*OUTPUT_FILE,$key); |
|
159 &write16(\*OUTPUT_FILE,$unicodeCharacterCodes{$key}); |
|
160 } |
|
161 } |
|
162 else |
|
163 { |
|
164 binmode OUTPUT_FILE; |
|
165 &writeBinaryHeader(\*OUTPUT_FILE, $uid, $endianness, $replacementForUnconvertibleUnicodeCharacters); |
|
166 &writeBinaryForeignVariableByteData(\*OUTPUT_FILE, \@foreignVariableByteData); |
|
167 &writeBinaryOneDirectionData(\*OUTPUT_FILE, \@foreignToUnicodeData, \%unicodeCharacterCodes, 1); |
|
168 &writeBinaryOneDirectionData(\*OUTPUT_FILE, \@unicodeToForeignData, \%foreignCharacterCodes, 0); |
|
169 } |
|
170 close(OUTPUT_FILE) or die("Error: could not close \"$outputFile\"\n"); |
|
171 print("complete\n\n"); |
|
172 |
|
173 sub extractCommandLineFlags() |
|
174 { |
|
175 my $generateSourceCode=shift; |
|
176 my $columns=shift; |
|
177 my $omitReplacementForUnconvertibleUnicodeCharacters=shift; |
|
178 my $cutOutAnyPrivateUseUnicodeCharacterSlotsBeingUsed=shift; |
|
179 my $sourceFilesToSubtract=shift; |
|
180 my $flattenHashAndSave=shift; |
|
181 my $i; |
|
182 for ($i=0; $i<=$#ARGV;) # (i) not cache-ing $#ARGV into a variable as @ARGV may change length in this loop (ii) iterate forwards as some parameters may occupy more than one element in @ARGV |
|
183 { |
|
184 if (($ARGV[$i]=~/^-s$/i) || ($ARGV[$i]=~/^-generateSourceCode$/i)) |
|
185 { |
|
186 if ($$flattenHashAndSave==1) |
|
187 { |
|
188 die ("Error: Cannot have -s and -b flags set at the same time"); |
|
189 } |
|
190 else |
|
191 { |
|
192 splice(@ARGV, $i, 1); |
|
193 $$generateSourceCode=1; |
|
194 } |
|
195 } |
|
196 elsif (($ARGV[$i]=~/^-c\b(.*)$/i) || ($ARGV[$i]=~/^-columns\b(.*)$/i)) |
|
197 { |
|
198 my $columnsData=$1; |
|
199 splice(@ARGV, $i, 1); |
|
200 for (;;) |
|
201 { |
|
202 if ($columnsData=~/^\s*\(\s*(\d+)\s*:\s*(\d+)\s*\,?\s*(\d+)\s*\)\s*$/) |
|
203 { |
|
204 @$columns=($1, $2, $3); |
|
205 last; |
|
206 } |
|
207 ($#ARGV>=$i) or die("Error: bad \"-columns\" format\n"); |
|
208 $columnsData.=(splice(@ARGV, $i, 1))[0]; |
|
209 } |
|
210 } |
|
211 elsif (($ARGV[$i]=~/^-r$/i) || ($ARGV[$i]=~/^-omitReplacementForUnconvertibleUnicodeCharacters$/i)) |
|
212 { |
|
213 splice(@ARGV, $i, 1); |
|
214 $$omitReplacementForUnconvertibleUnicodeCharacters=1; |
|
215 } |
|
216 elsif (($ARGV[$i]=~/^-p$/i) || ($ARGV[$i]=~/^-cutOutAnyPrivateUseUnicodeCharacterSlotsBeingUsed$/i)) |
|
217 { |
|
218 splice(@ARGV, $i, 1); |
|
219 $$cutOutAnyPrivateUseUnicodeCharacterSlotsBeingUsed=1; |
|
220 } |
|
221 elsif (($ARGV[$i]=~/^-u\b(.*)$/i) || ($ARGV[$i]=~/^-sourceFilesToSubtract\b(.*)$/i)) |
|
222 { |
|
223 my $sourceFilesData=$1; |
|
224 splice(@ARGV, $i, 1); |
|
225 for (;;) |
|
226 { |
|
227 if ($sourceFilesData=~/^\s*\(\s*(.+)\)\s*$/) |
|
228 { |
|
229 my $sourceFilesData=$1; |
|
230 @$sourceFilesToSubtract=split(/,/, $sourceFilesData, -1); |
|
231 my $j; |
|
232 for ($j=$#$sourceFilesToSubtract; $j>=0; --$j) |
|
233 { |
|
234 $sourceFilesToSubtract->[$j]=~s/^\s+//; |
|
235 $sourceFilesToSubtract->[$j]=~s/\s+$//; |
|
236 ($sourceFilesToSubtract->[$j] ne '') or die("Error: bad \"-sourceFilesToSubtract\" format (1)\n"); |
|
237 } |
|
238 last; |
|
239 } |
|
240 ($#ARGV>=$i) or die("Error: bad \"-sourceFilesToSubtract\" format (2)\n"); |
|
241 $sourceFilesData.=(splice(@ARGV, $i, 1))[0]; |
|
242 } |
|
243 } |
|
244 elsif (($ARGV[$i]=~/^-f$/i) || ($ARGV[$i]=~/^-flattenHashAndSave$/i)) |
|
245 { |
|
246 if ($$generateSourceCode==1) |
|
247 { |
|
248 die ("Error: Cannot have -s and -b flags set at the same time"); |
|
249 } |
|
250 else |
|
251 { |
|
252 splice(@ARGV, $i, 1); |
|
253 $$flattenHashAndSave=1; |
|
254 } |
|
255 } |
|
256 else |
|
257 { |
|
258 ++$i; |
|
259 } |
|
260 } |
|
261 } |
|
262 |
|
263 sub algorithm |
|
264 { |
|
265 my $algorithmAsText=shift; |
|
266 if ($algorithmAsText=~/^Direct$/i) |
|
267 { |
|
268 return 0; |
|
269 } |
|
270 elsif ($algorithmAsText=~/^Offset$/i) |
|
271 { |
|
272 return 1; |
|
273 } |
|
274 elsif ($algorithmAsText=~/^IndexedTable16$/i) |
|
275 { |
|
276 return 2; |
|
277 } |
|
278 elsif ($algorithmAsText=~/^KeyedTable1616$/i) |
|
279 { |
|
280 return 3; |
|
281 } |
|
282 elsif ($algorithmAsText=~/^KeyedTable16OfIndexedTables16$/i) |
|
283 { |
|
284 return 4; |
|
285 } |
|
286 elsif ($algorithmAsText=~/^IndexedTable32$/i) |
|
287 { |
|
288 return 5; |
|
289 } |
|
290 elsif ($algorithmAsText=~/^KeyedTable3232$/i) |
|
291 { |
|
292 return 6; |
|
293 } |
|
294 elsif ($algorithmAsText=~/^KeyedTable32OfIndexedTables32$/i) |
|
295 { |
|
296 return 7; |
|
297 } |
|
298 else |
|
299 { |
|
300 return -1; |
|
301 } |
|
302 } |
|
303 |
|
304 sub hexadecimalify |
|
305 { |
|
306 my $string=shift; |
|
307 my $result=''; |
|
308 my $lengthOfString=length($string); |
|
309 my $i; |
|
310 for ($i=0; $i<$lengthOfString; ++$i) |
|
311 { |
|
312 $result.=sprintf("\\x%02x", (unpack('C', substr($string, $i, 1)))[0]); |
|
313 } |
|
314 return $result; |
|
315 } |
|
316 |
|
317 sub readSourceFile |
|
318 { |
|
319 my $fileHandle=shift; |
|
320 my $fileName=shift; |
|
321 my $foreignCharacterCodes=shift; |
|
322 my $unicodeCharacterCodes=shift; |
|
323 my $columns=shift; |
|
324 my $cutOutAnyPrivateUseUnicodeCharacterSlotsBeingUsed=shift; |
|
325 my $privateUseUnicodeCharacterSlotsUsed=shift; |
|
326 my $subtract=shift; |
|
327 my $foreignCharacterCodeProcessingCode=''; |
|
328 if (!(($columns->[0]>0) && ($columns->[1]>0) && ($columns->[2]>0) && ($columns->[1]<=$columns->[0]) && ($columns->[2]<=$columns->[0]) && ($columns->[1]!=$columns->[2]))) |
|
329 { |
|
330 close($fileHandle); |
|
331 die("Error: bad \"-columns\" data\n"); |
|
332 } |
|
333 my $patternOfLineContainingCharacterCodes=join('\s+', ('0x([0-9a-f]+)') x $columns->[0]); |
|
334 my $line; |
|
335 my $strippedDownLine; |
|
336 for (;;) |
|
337 { |
|
338 ($line, $strippedDownLine)=&nextNonEmptyStrippedDownLine($fileHandle); |
|
339 if (($strippedDownLine eq '')||(substr($strippedDownLine,0,1) eq chr(26))) # if there are no more lines in the file or if we encountered EOF character |
|
340 { |
|
341 last; |
|
342 } |
|
343 if ($strippedDownLine=~/^SET_FOREIGN_CHARACTER_CODE_PROCESSING_CODE\s+(.*)$/i) |
|
344 { |
|
345 $foreignCharacterCodeProcessingCode=$1; |
|
346 } |
|
347 elsif ($strippedDownLine=~/^$patternOfLineContainingCharacterCodes$/i) |
|
348 { |
|
349 no strict 'refs'; # so that we can use symbolic references for $1, $2, etc |
|
350 my $foreignCharacterCode=hex(${$columns->[1]}); |
|
351 my $unicodeCharacterCode=hex(${$columns->[2]}); |
|
352 use strict 'refs'; |
|
353 if ($foreignCharacterCodeProcessingCode ne '') |
|
354 { |
|
355 $foreignCharacterCode=eval($foreignCharacterCodeProcessingCode); |
|
356 } |
|
357 my $handleConversionPair=1; |
|
358 if ((($unicodeCharacterCode>=0xe000) && ($unicodeCharacterCode<=0xf8ff)) || (($unicodeCharacterCode>=0xf0000) && ($unicodeCharacterCode<=0x10ffff))) |
|
359 { |
|
360 if ($cutOutAnyPrivateUseUnicodeCharacterSlotsBeingUsed) |
|
361 { |
|
362 $handleConversionPair=0; |
|
363 } |
|
364 else |
|
365 { |
|
366 if ($subtract) |
|
367 { |
|
368 delete $privateUseUnicodeCharacterSlotsUsed->{$unicodeCharacterCode}; |
|
369 } |
|
370 else |
|
371 { |
|
372 $privateUseUnicodeCharacterSlotsUsed->{$unicodeCharacterCode}=1; |
|
373 } |
|
374 } |
|
375 } |
|
376 if ($handleConversionPair) |
|
377 { |
|
378 if ($subtract) |
|
379 { |
|
380 if (!defined($foreignCharacterCodes->{$unicodeCharacterCode}->{$foreignCharacterCode})) |
|
381 { |
|
382 close($fileHandle); |
|
383 die('Error: cannot subtract conversion pair ['.sprintf('foreign 0x%x, Unicode 0x%04x', $foreignCharacterCode, $unicodeCharacterCode)."] as it does not occur in \"$fileName\"\n"); |
|
384 } |
|
385 if (!defined($unicodeCharacterCodes->{$foreignCharacterCode}->{$unicodeCharacterCode})) |
|
386 { |
|
387 close($fileHandle); |
|
388 die('Error: cannot subtract conversion pair ['.sprintf('Unicode 0x%04x, foreign 0x%x', $unicodeCharacterCode, $foreignCharacterCode)."] as it does not occur in \"$fileName\"\n"); |
|
389 } |
|
390 delete $foreignCharacterCodes->{$unicodeCharacterCode}->{$foreignCharacterCode}; |
|
391 if (keys(%{$foreignCharacterCodes->{$unicodeCharacterCode}})==0) |
|
392 { |
|
393 delete $foreignCharacterCodes->{$unicodeCharacterCode}; |
|
394 } |
|
395 delete $unicodeCharacterCodes->{$foreignCharacterCode}->{$unicodeCharacterCode}; |
|
396 if (keys(%{$unicodeCharacterCodes->{$foreignCharacterCode}})==0) |
|
397 { |
|
398 delete $unicodeCharacterCodes->{$foreignCharacterCode}; |
|
399 } |
|
400 } |
|
401 else |
|
402 { |
|
403 if (defined($foreignCharacterCodes->{$unicodeCharacterCode}->{$foreignCharacterCode})) |
|
404 { |
|
405 close($fileHandle); |
|
406 die('Error: same conversion pair ['.sprintf('foreign 0x%x, Unicode 0x%04x', $foreignCharacterCode, $unicodeCharacterCode)."] occurs more than once in \"$fileName\"\n"); |
|
407 } |
|
408 if (defined($unicodeCharacterCodes->{$foreignCharacterCode}->{$unicodeCharacterCode})) |
|
409 { |
|
410 close($fileHandle); |
|
411 die('Error: same conversion pair ['.sprintf('Unicode 0x%04x, foreign 0x%x', $unicodeCharacterCode, $foreignCharacterCode)."] occurs more than once in \"$fileName\"\n"); |
|
412 } |
|
413 $foreignCharacterCodes->{$unicodeCharacterCode}->{$foreignCharacterCode}=1; |
|
414 $unicodeCharacterCodes->{$foreignCharacterCode}->{$unicodeCharacterCode}=1; |
|
415 } |
|
416 } |
|
417 } |
|
418 elsif ($line!~/^\s*0x([0-9a-f]+)\s*#\s*undefined.*$/i) |
|
419 { |
|
420 close($fileHandle); |
|
421 die("Error: unexpected line in \"$fileName\":\n $line\n"); |
|
422 } |
|
423 } |
|
424 } |
|
425 |
|
426 sub readHeaderFromControlFile |
|
427 { |
|
428 my $fileHandle=shift; |
|
429 my $fileName=shift; |
|
430 my $generateSourceCode=shift; |
|
431 my $uid=shift; |
|
432 my $endiannessAsText=shift; |
|
433 my $endianness=shift; |
|
434 my $replacementForUnconvertibleUnicodeCharacters=shift; |
|
435 my $flattenHashAndSave=shift; |
|
436 my $line; |
|
437 my $strippedDownLine; |
|
438 ($line, $strippedDownLine)=&nextNonEmptyStrippedDownLine($fileHandle); |
|
439 if ($strippedDownLine=~/^UID\s+0x([0-9a-f]+)$/i) |
|
440 { |
|
441 if ($generateSourceCode) |
|
442 { |
|
443 print(STDERR "Warning: \"UID\" keyword should not be used with \"-generateSourceCode\" flag - specify the UID in the MMP file\n"); |
|
444 } |
|
445 $$uid=hex($1); |
|
446 ($line, $strippedDownLine)=&nextNonEmptyStrippedDownLine($fileHandle); |
|
447 } |
|
448 else |
|
449 { |
|
450 if (!$generateSourceCode && !$flattenHashAndSave) |
|
451 { |
|
452 close($fileHandle); |
|
453 die("Error: unexpected line in \"$fileName\" (\"UID\" keyword expected):\n $line\n"); |
|
454 } |
|
455 } |
|
456 if ($strippedDownLine=~/^Name\s+"(.+?)"$/i) |
|
457 { |
|
458 print(STDERR "Warning: obsolete keyword \"Name\" used\n"); |
|
459 ($line, $strippedDownLine)=&nextNonEmptyStrippedDownLine($fileHandle); |
|
460 } |
|
461 if ($strippedDownLine!~/^Endianness\s+(\w+)$/i) |
|
462 { |
|
463 close($fileHandle); |
|
464 die("Error: unexpected line in \"$fileName\" (\"Endianness\" keyword expected):\n $line\n"); |
|
465 } |
|
466 $$endiannessAsText=$1; |
|
467 if ($$endiannessAsText=~/Unspecified/i) |
|
468 { |
|
469 $$endianness=0; # SCnvConversionData::EUnspecified |
|
470 } |
|
471 elsif ($$endiannessAsText=~/FixedLittleEndian/i) |
|
472 { |
|
473 $$endianness=1; # SCnvConversionData::EFixedLittleEndian |
|
474 } |
|
475 elsif ($$endiannessAsText=~/FixedBigEndian/i) |
|
476 { |
|
477 $$endianness=2; # SCnvConversionData::EFixedBigEndian |
|
478 } |
|
479 else |
|
480 { |
|
481 close($fileHandle); |
|
482 die("Error: \"$$endiannessAsText\" is not a legal value for \"Endianness\"\n"); |
|
483 } |
|
484 ($line, $strippedDownLine)=&nextNonEmptyStrippedDownLine($fileHandle); |
|
485 if ($strippedDownLine!~/^ReplacementForUnconvertibleUnicodeCharacters\s+(.*?)$/i) |
|
486 { |
|
487 close($fileHandle); |
|
488 die("Error: unexpected line in \"$fileName\" (\"ReplacementForUnconvertibleUnicodeCharacters\" keyword expected):\n $line\n"); |
|
489 } |
|
490 $$replacementForUnconvertibleUnicodeCharacters=''; |
|
491 my $remainderOfXxx=$1; |
|
492 while ($remainderOfXxx ne '') |
|
493 { |
|
494 if ($remainderOfXxx!~/^0x([0-9a-f]{1,2})\s*(.*)$/i) |
|
495 { |
|
496 close($fileHandle); |
|
497 die("Error: unexpected line in \"$fileName\":\n $line\n"); |
|
498 } |
|
499 $$replacementForUnconvertibleUnicodeCharacters.=pack("C", hex($1)); |
|
500 $remainderOfXxx=$2; |
|
501 } |
|
502 my @temp=&nextNonEmptyStrippedDownLine($fileHandle); |
|
503 if ($temp[1]=~/^ForeignCharacterCodeProcessingCode/i) |
|
504 { |
|
505 print(STDERR "Warning: obsolete keyword \"ForeignCharacterCodeProcessingCode\" used\n"); |
|
506 } |
|
507 else |
|
508 { |
|
509 ungetNonEmptyStrippedDownLine(@temp) |
|
510 } |
|
511 } |
|
512 |
|
513 sub readForeignVariableByteDataFromControlFile |
|
514 { |
|
515 my $fileHandle=shift; |
|
516 my $fileName=shift; |
|
517 my $foreignVariableByteData=shift; |
|
518 my $line; |
|
519 my $strippedDownLine; |
|
520 ($line, $strippedDownLine)=&nextNonEmptyStrippedDownLine($fileHandle); |
|
521 if ($strippedDownLine!~/^StartForeignVariableByteData$/i) |
|
522 { |
|
523 close($fileHandle); |
|
524 die("Error: unexpected line in \"$fileName\":\n $line\n"); |
|
525 } |
|
526 |
|
527 for (;;) |
|
528 { |
|
529 ($line, $strippedDownLine)=&nextNonEmptyStrippedDownLine($fileHandle); |
|
530 if ($strippedDownLine=~/^EndForeignVariableByteData$/i) |
|
531 { |
|
532 last; |
|
533 } |
|
534 if ($strippedDownLine!~/^0x([0-9a-f]+)\s+0x([0-9a-f]+)\s+(\d+)$/i) |
|
535 { |
|
536 close($fileHandle); |
|
537 die("Error: unexpected line in \"$fileName\":\n $line\n"); |
|
538 } |
|
539 my $firstInitialByteValueInRange=hex($1); |
|
540 my $lastInitialByteValueInRange=hex($2); |
|
541 my $numberOfSubsequentBytes=$3; |
|
542 if ($firstInitialByteValueInRange>0xff) |
|
543 { |
|
544 close($fileHandle); |
|
545 die("Error: firstInitialByteValueInRange ".sprintf("0x%02x", $firstInitialByteValueInRange)." does not fit in a single byte\n"); |
|
546 } |
|
547 if ($lastInitialByteValueInRange>0xff) |
|
548 { |
|
549 close($fileHandle); |
|
550 die("Error: lastInitialByteValueInRange ".sprintf("0x%02x", $lastInitialByteValueInRange)." does not fit in a single byte\n"); |
|
551 } |
|
552 if ($lastInitialByteValueInRange<$firstInitialByteValueInRange) |
|
553 { |
|
554 close($fileHandle); |
|
555 die("Error: lastInitialByteValueInRange ".sprintf("0x%02x", $lastInitialByteValueInRange)." is less than firstInitialByteValueInRange ".sprintf("0x%02x", $firstInitialByteValueInRange)."\n"); |
|
556 } |
|
557 push(@$foreignVariableByteData, [$firstInitialByteValueInRange, $lastInitialByteValueInRange, $numberOfSubsequentBytes]); |
|
558 } |
|
559 } |
|
560 |
|
561 sub readOneDirectionDataFromControlFile |
|
562 { |
|
563 my $fileHandle=shift; |
|
564 my $fileName=shift; |
|
565 my $oneDirectionData=shift; |
|
566 my $preferredCharacterCodesForConflictResolution=shift; |
|
567 my $additionalSubsetTables=shift; |
|
568 my $outputIsUnicode=shift; |
|
569 my $source=$outputIsUnicode? 'foreign': 'Unicode'; |
|
570 my $target=$outputIsUnicode? 'Unicode': 'foreign'; |
|
571 my $middlePortionOfKeyWords=$outputIsUnicode? "ForeignToUnicode": "UnicodeToForeign"; |
|
572 my $extraPatternToMatch=$outputIsUnicode? '()': '\s+(\d+)'; |
|
573 my $line; |
|
574 my $strippedDownLine; |
|
575 ($line, $strippedDownLine)=&nextNonEmptyStrippedDownLine($fileHandle); |
|
576 if ($strippedDownLine!~/^Start${middlePortionOfKeyWords}Data$/i) |
|
577 { |
|
578 close($fileHandle); |
|
579 die("Error: unexpected line in \"$fileName\":\n $line\n"); |
|
580 } |
|
581 my $doingConflictResolution=0; |
|
582 for (;;) |
|
583 { |
|
584 ($line, $strippedDownLine)=&nextNonEmptyStrippedDownLine($fileHandle); |
|
585 if ($strippedDownLine=~/^End${middlePortionOfKeyWords}Data$/i) |
|
586 { |
|
587 last; |
|
588 } |
|
589 if ($strippedDownLine=~/^ConflictResolution$/i) |
|
590 { |
|
591 $doingConflictResolution=1; |
|
592 } |
|
593 elsif ($doingConflictResolution) |
|
594 { |
|
595 if ($strippedDownLine!~/^0x([0-9a-f]+)\s+0x([0-9a-f]+)$/i) |
|
596 { |
|
597 close($fileHandle); |
|
598 die("Error: unexpected line in \"$fileName\":\n $line\n"); |
|
599 } |
|
600 my $sourceCharacterCodeToResolve=hex($1); |
|
601 my $targetCharacterCodePreferred=hex($2); |
|
602 $preferredCharacterCodesForConflictResolution->{$sourceCharacterCodeToResolve}=$targetCharacterCodePreferred; |
|
603 } |
|
604 elsif ($strippedDownLine=~/^(Start|End)AdditionalSubsetTable\s+(.*)$/i) |
|
605 { |
|
606 my $prefix=$1; |
|
607 my $nameOfAdditionalSubsetTable=$2; |
|
608 my $index=$prefix=~(/^Start$/i)? 0: 1; |
|
609 if (!$outputIsUnicode) |
|
610 { |
|
611 $index+=2; |
|
612 } |
|
613 if (defined($additionalSubsetTables{$nameOfAdditionalSubsetTable}->[$index])) |
|
614 { |
|
615 close($fileHandle); |
|
616 die("Error: multiple redefinition of \"${prefix}AdditionalSubsetTable $nameOfAdditionalSubsetTable\"\n"); |
|
617 } |
|
618 $additionalSubsetTables{$nameOfAdditionalSubsetTable}->[$index]=@$oneDirectionData; |
|
619 } |
|
620 else |
|
621 { |
|
622 if ($strippedDownLine!~/^(\d+)\s+(\d+)\s+0x([0-9a-f]+)\s+0x([0-9a-f]+)\s+(\w+)$extraPatternToMatch\s+\{(.*?)\}$/i) |
|
623 { |
|
624 close($fileHandle); |
|
625 die("Error: unexpected line in \"$fileName\":\n $line\n"); |
|
626 } |
|
627 my $includePriority=$1; |
|
628 my $searchPriority=$2; |
|
629 my $firstInputCharacterCodeInRange=hex($3); |
|
630 my $lastInputCharacterCodeInRange=hex($4); |
|
631 my $algorithmAsText=$5; |
|
632 my $sizeOfOutputCharacterCodeInBytes=$6; |
|
633 my $parameters=$7; |
|
634 if ($lastInputCharacterCodeInRange<$firstInputCharacterCodeInRange) |
|
635 { |
|
636 close($fileHandle); |
|
637 die("Error: lastInputCharacterCodeInRange ".sprintf("0x%02x", $lastInputCharacterCodeInRange)." is less than firstInputCharacterCodeInRange ".sprintf("0x%02x", $firstInputCharacterCodeInRange)."\n"); |
|
638 } |
|
639 my $algorithm=&algorithm($algorithmAsText); |
|
640 if ($algorithm<0) |
|
641 { |
|
642 close($fileHandle); |
|
643 die("Error: unexpected algorithm \"$algorithmAsText\"\n"); |
|
644 } |
|
645 my $rangeData=[$includePriority, $searchPriority, $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange, $algorithm]; |
|
646 if (!$outputIsUnicode) |
|
647 { |
|
648 push(@$rangeData, $sizeOfOutputCharacterCodeInBytes); |
|
649 } |
|
650 push(@$rangeData, $parameters); |
|
651 push(@$oneDirectionData, $rangeData); |
|
652 } |
|
653 } |
|
654 } |
|
655 |
|
656 sub warnIfAnyPrivateUseUnicodeCharacterSlotsBeingUsed |
|
657 { |
|
658 my $privateUseUnicodeCharacterSlotsUsed=shift; |
|
659 my @sortedPrivateUseUnicodeCharacterSlotsUsed=sort({$a<=>$b} keys(%$privateUseUnicodeCharacterSlotsUsed)); |
|
660 if (@sortedPrivateUseUnicodeCharacterSlotsUsed>0) |
|
661 { |
|
662 my $lastPrivateUseUnicodeCharacterSlotUsed=$sortedPrivateUseUnicodeCharacterSlotsUsed[0]; |
|
663 my $asText=sprintf('0x%04x', $lastPrivateUseUnicodeCharacterSlotUsed); |
|
664 my @asText=($asText); |
|
665 my $i; |
|
666 for ($i=1; $i<@sortedPrivateUseUnicodeCharacterSlotsUsed; ++$i) # this loop starts from 1 not 0 as we have already dealt with $sortedPrivateUseUnicodeCharacterSlotsUsed[0] |
|
667 { |
|
668 ($sortedPrivateUseUnicodeCharacterSlotsUsed[$i]>$lastPrivateUseUnicodeCharacterSlotUsed) or die("Error: internal error 1\n"); |
|
669 if ($sortedPrivateUseUnicodeCharacterSlotsUsed[$i]>$lastPrivateUseUnicodeCharacterSlotUsed+1) |
|
670 { |
|
671 $asText=sprintf('0x%04x', $lastPrivateUseUnicodeCharacterSlotUsed); |
|
672 if ($asText[-1] ne $asText) |
|
673 { |
|
674 $asText[-1].='-'.$asText; |
|
675 } |
|
676 push(@asText, sprintf('0x%04x', $sortedPrivateUseUnicodeCharacterSlotsUsed[$i])); |
|
677 } |
|
678 $lastPrivateUseUnicodeCharacterSlotUsed=$sortedPrivateUseUnicodeCharacterSlotsUsed[$i]; |
|
679 } |
|
680 $asText=sprintf('0x%04x', $lastPrivateUseUnicodeCharacterSlotUsed); |
|
681 if ($asText[-1] ne $asText) |
|
682 { |
|
683 $asText[-1].='-'.$asText; |
|
684 } |
|
685 print(STDERR 'Warning: the following private-use Unicode character slots were used: ['.join(', ', @asText)."]\n"); |
|
686 } |
|
687 } |
|
688 |
|
689 sub resolveConflictsAndFlattenArraysToScalars |
|
690 { |
|
691 my $characterCodes=shift; |
|
692 my $preferredCharacterCodesForConflictResolution=shift; |
|
693 my $source=shift; |
|
694 my $target=shift; |
|
695 my $sourceCharacterCode; |
|
696 my $candidateTargetCharacterCodes; |
|
697 while (($sourceCharacterCode, $candidateTargetCharacterCodes)=each(%$characterCodes)) |
|
698 { |
|
699 my @candidateTargetCharacterCodes=keys(%$candidateTargetCharacterCodes); |
|
700 if (@candidateTargetCharacterCodes<1) |
|
701 { |
|
702 die("Error: internal error 2\n"); |
|
703 } |
|
704 if (@candidateTargetCharacterCodes==1) |
|
705 { |
|
706 $characterCodes->{$sourceCharacterCode}=$candidateTargetCharacterCodes[0]; |
|
707 } |
|
708 else |
|
709 { |
|
710 if (!defined($preferredCharacterCodesForConflictResolution->{$sourceCharacterCode})) |
|
711 { |
|
712 die("Error: no preferred $target character code is specified for conflict resolution for the $source character code ".sprintf("0x%08x", $sourceCharacterCode)."\n"); |
|
713 } |
|
714 my $preferredCharacterCodeIsNotACandidateForConflictResolution=1; |
|
715 my $candidateTargetCharacterCode; |
|
716 foreach $candidateTargetCharacterCode (@candidateTargetCharacterCodes) |
|
717 { |
|
718 if ($preferredCharacterCodesForConflictResolution->{$sourceCharacterCode}==$candidateTargetCharacterCode) |
|
719 { |
|
720 $preferredCharacterCodeIsNotACandidateForConflictResolution=0; |
|
721 last; |
|
722 } |
|
723 } |
|
724 if ($preferredCharacterCodeIsNotACandidateForConflictResolution) |
|
725 { |
|
726 die("Error: the preferred $target character code ".sprintf("0x%08x", $preferredCharacterCodesForConflictResolution->{$sourceCharacterCode})." is not a candidate for conflict resolution for the $source character code ".sprintf("0x%08x", $sourceCharacterCode)."\n"); |
|
727 } |
|
728 $characterCodes->{$sourceCharacterCode}=$preferredCharacterCodesForConflictResolution->{$sourceCharacterCode}; |
|
729 delete $preferredCharacterCodesForConflictResolution->{$sourceCharacterCode}; |
|
730 } |
|
731 } |
|
732 my $numberOfPreferredCharacterCodesForConflictResolution=keys(%$preferredCharacterCodesForConflictResolution); |
|
733 if ($numberOfPreferredCharacterCodesForConflictResolution!=0) |
|
734 { |
|
735 print(STDERR "Warning: there are $numberOfPreferredCharacterCodesForConflictResolution $target preferred character codes specified for which there are no conflicts to resolve\n"); |
|
736 } |
|
737 } |
|
738 |
|
739 sub checkForeignVariableByteData |
|
740 { |
|
741 my $endianness=shift; |
|
742 my $foreignVariableByteData=shift; |
|
743 my $foreignToUnicodeData=shift; |
|
744 my $rangeData; |
|
745 my %initialForeignBytes=(); |
|
746 foreach $rangeData (@$foreignVariableByteData) |
|
747 { |
|
748 my $initialByte; |
|
749 for ($initialByte=$rangeData->[0]; $initialByte<=$rangeData->[1]; ++$initialByte) |
|
750 { |
|
751 if (defined($initialForeignBytes{$initialByte})) |
|
752 { |
|
753 die("Error: the number of bytes subsequent to the initial foreign-byte $initialForeignBytes{$initialByte} is defined more than once\n"); |
|
754 } |
|
755 $initialForeignBytes{$initialByte}=1; |
|
756 } |
|
757 } |
|
758 # if ($endianness!=0) # unfortunately, nothing can be checked if the $endianness is 0 (SCnvConversionData::EUnspecified) |
|
759 # { |
|
760 # foreach $rangeData (@$foreignToUnicodeData) |
|
761 # { |
|
762 # my $inputCharacterCode; |
|
763 # for ($inputCharacterCode=$rangeData->[2]; $inputCharacterCode<=$rangeData->[3]; ++$inputCharacterCode) |
|
764 # { |
|
765 # my $initialByte; |
|
766 # if ($endianness==1) # SCnvConversionData::EFixedLittleEndian |
|
767 # { |
|
768 # $initialByte=($inputCharacterCode&0xff); |
|
769 # } |
|
770 # elsif ($endianness==2) # SCnvConversionData::EFixedBigEndian |
|
771 # { |
|
772 # $initialByte=($inputCharacterCode&0xff00)>>8; ## this is hard-coded and needs to be done properly! |
|
773 # } |
|
774 # else |
|
775 # { |
|
776 # die("Error: internal error ??\n"); |
|
777 # } |
|
778 # if (!defined($initialForeignBytes{$initialByte})) |
|
779 # { |
|
780 # die("Error: no number-of-subsequent-bytes is specified for the initial byte $initialByte\n"); |
|
781 # } |
|
782 # } |
|
783 # } |
|
784 # } |
|
785 } |
|
786 |
|
787 sub writeSourceCodeHeader |
|
788 { |
|
789 my $fileHandle=shift; |
|
790 my $fileName=shift; |
|
791 my $replacementForUnconvertibleUnicodeCharacters=shift; |
|
792 while ($fileName=~/^.*\\(.*)$/i) |
|
793 { |
|
794 $fileName=$1; |
|
795 } |
|
796 print($fileHandle "// $fileName\n//\n// Copyright (c) Nokia Corporation and/or its subsidiary(-ies) ".(1900+(gmtime(time))[5]).". All rights reserved.\n//\n\n"); |
|
797 print($fileHandle "#include <e32std.h>\n#include <convdata.h>\n#include <convgeneratedcpp.h>\n\n#define ARRAY_LENGTH(aArray) (sizeof(aArray)/sizeof((aArray)\[0\]))\n\n#pragma warning (disable: 4049) // compiler limit : terminating line number emission\n\n"); |
|
798 if (!$omitReplacementForUnconvertibleUnicodeCharacters) |
|
799 { |
|
800 print($fileHandle "_LIT8(KLit8ReplacementForUnconvertibleUnicodeCharacters, \"".&hexadecimalify($replacementForUnconvertibleUnicodeCharacters)."\");\n\n"); |
|
801 print($fileHandle "GLDEF_C const TDesC8& ReplacementForUnconvertibleUnicodeCharacters_internal()\n\t{\n\treturn KLit8ReplacementForUnconvertibleUnicodeCharacters;\n\t}\n\n"); |
|
802 } |
|
803 } |
|
804 |
|
805 sub writeSourceCodeForeignVariableByteData |
|
806 { |
|
807 my $sourceCodeOfTopLevelStructures=shift; |
|
808 my $foreignVariableByteData=shift; |
|
809 push(@$sourceCodeOfTopLevelStructures, "LOCAL_D const SCnvConversionData::SVariableByteData::SRange foreignVariableByteDataRanges[]=\n\t\{\n"); |
|
810 my $indexOfLastRange=$#$foreignVariableByteData; |
|
811 my $i; |
|
812 for ($i=0; $i<=$indexOfLastRange; ++$i) |
|
813 { |
|
814 my $rangeData=$foreignVariableByteData->[$i]; |
|
815 if (@$rangeData!=3) |
|
816 { |
|
817 die("Error: internal error 3\n"); |
|
818 } |
|
819 my $firstInitialByteValueInRange=$rangeData->[0]; |
|
820 my $lastInitialByteValueInRange=$rangeData->[1]; |
|
821 if ($lastInitialByteValueInRange<$firstInitialByteValueInRange) |
|
822 { |
|
823 die("Error: internal error 4\n"); |
|
824 } |
|
825 my $numberOfSubsequentBytes=$rangeData->[2]; |
|
826 push(@$sourceCodeOfTopLevelStructures, "\t\t\{\n\t\t".sprintf("0x%02x", $firstInitialByteValueInRange).",\n\t\t".sprintf("0x%02x", $lastInitialByteValueInRange).",\n\t\t$numberOfSubsequentBytes,\n\t\t0\n\t\t\}"); |
|
827 if ($i<$indexOfLastRange) |
|
828 { |
|
829 push(@$sourceCodeOfTopLevelStructures, ','); |
|
830 } |
|
831 push(@$sourceCodeOfTopLevelStructures, "\n"); |
|
832 } |
|
833 push(@$sourceCodeOfTopLevelStructures, "\t\};\n\n"); |
|
834 } |
|
835 |
|
836 sub writeSourceCodeOneDirectionData |
|
837 { |
|
838 my $sourceCodeOfTopLevelStructures=shift; |
|
839 my $sourceCodeOfOneDirectionIndexedTables16=shift; |
|
840 my $sourceCodeOfOneDirectionKeyedTables1616=shift; |
|
841 my $sourceCodeOfOneDirectionKeyedTables16OfIndexedTables16_indexedEntries=shift; |
|
842 my $sourceCodeOfOneDirectionKeyedTables16OfIndexedTables16_keyedEntries=shift; |
|
843 # new for 32 bit encoding begin |
|
844 my $sourceCodeOfOneDirectionIndexedTables32=shift; |
|
845 my $sourceCodeOfOneDirectionKeyedTables3232=shift; |
|
846 my $sourceCodeOfOneDirectionKeyedTables32OfIndexedTables32_indexedEntries=shift; |
|
847 my $sourceCodeOfOneDirectionKeyedTables32OfIndexedTables32_keyedEntries=shift; |
|
848 # new for 32 bit encoding end |
|
849 |
|
850 my $oneDirectionData=shift; |
|
851 my $characterCodes=shift; |
|
852 my $outputIsUnicode=shift; |
|
853 push(@$sourceCodeOfTopLevelStructures, 'LOCAL_D const SCnvConversionData::SOneDirectionData::SRange '.($outputIsUnicode? 'foreignToUnicodeDataRanges': 'unicodeToForeignDataRanges')."[]=\n\t\{\n"); |
|
854 my $formatForInputCharacters=$outputIsUnicode? '0x%02x': '0x%04x'; |
|
855 my $formatForOutputCharacters=$outputIsUnicode? '0x%04x': '0x%02x'; |
|
856 my $indexOfLastRange=$#$oneDirectionData; |
|
857 my $i; |
|
858 for ($i=0; $i<=$indexOfLastRange; ++$i) |
|
859 { |
|
860 my $rangeData=$oneDirectionData->[$i]; |
|
861 # $rangeData is $includePriority, $searchPriority, $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange, $algorithm[, $sizeOfOutputCharacterCodeInBytes], $parameters |
|
862 if (scalar(@$rangeData)!=($outputIsUnicode? 6: 7)) |
|
863 { |
|
864 die("Error: internal error 5\n"); |
|
865 } |
|
866 my $firstInputCharacterCodeInRange=$rangeData->[2]; |
|
867 my $lastInputCharacterCodeInRange=$rangeData->[3]; |
|
868 if ($lastInputCharacterCodeInRange<$firstInputCharacterCodeInRange) |
|
869 { |
|
870 die("Error: internal error 6\n"); |
|
871 } |
|
872 my $algorithmAsText=''; # set by the if-elsif stuff below |
|
873 my $sizeOfOutputCharacterCodeInBytesIfForeign=$outputIsUnicode? 0: $rangeData->[5]; |
|
874 my $parameters=$rangeData->[$outputIsUnicode? 5: 6]; |
|
875 my $word1=0; # set by the if-elsif stuff below |
|
876 my $algorithm=$rangeData->[4]; |
|
877 if ($algorithm==0) # Direct |
|
878 { |
|
879 $algorithmAsText='Direct'; |
|
880 my $characterCode; |
|
881 for ($characterCode=$firstInputCharacterCodeInRange; $characterCode<=$lastInputCharacterCodeInRange; ++$characterCode) |
|
882 { |
|
883 if (!defined($characterCodes->{$characterCode})) |
|
884 { |
|
885 die("Error: There is no conversion defined for ".($outputIsUnicode? 'foreign': 'Unicode')." character code ".sprintf("0x%08x", $characterCode)."\n"); |
|
886 } |
|
887 if ($characterCodes->{$characterCode}!=$characterCode) |
|
888 { |
|
889 die("Error: the conversion from ".($outputIsUnicode? 'foreign': 'Unicode')." character code ".sprintf("0x%08x", $characterCode)." to ".($outputIsUnicode? 'Unicode': 'foreign')." character code ".sprintf("0x%08x", $characterCodes->{$characterCode})." is not a direct conversion\n"); |
|
890 } |
|
891 delete $characterCodes->{$characterCode}; |
|
892 } |
|
893 } |
|
894 elsif ($algorithm==1) # Offset |
|
895 { |
|
896 $algorithmAsText='Offset'; |
|
897 my $offset=$characterCodes->{$firstInputCharacterCodeInRange}-$firstInputCharacterCodeInRange; |
|
898 delete $characterCodes->{$firstInputCharacterCodeInRange}; |
|
899 my $characterCode; |
|
900 for ($characterCode=$firstInputCharacterCodeInRange+1; $characterCode<=$lastInputCharacterCodeInRange; ++$characterCode) |
|
901 { |
|
902 if (!defined($characterCodes->{$characterCode})) |
|
903 { |
|
904 die("Error: There is no conversion defined for ".($outputIsUnicode? 'foreign': 'Unicode')." character code ".sprintf("0x%08x (0x%08x-0x%08x)", $characterCode, $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange)."\n"); |
|
905 } |
|
906 if ($characterCodes->{$characterCode}-$characterCode!=$offset) |
|
907 { |
|
908 die("Error: the conversion from ".($outputIsUnicode? 'foreign': 'Unicode')." character code ".sprintf("0x%08x", $characterCode)." to ".($outputIsUnicode? 'Unicode': 'foreign')." character code ".sprintf("0x%08x", $characterCodes->{$characterCode})." has a different offset from the previous one in the range\n"); |
|
909 } |
|
910 delete $characterCodes->{$characterCode}; |
|
911 } |
|
912 $word1="STATIC_CAST(TUint, $offset)"; |
|
913 } |
|
914 elsif ($algorithm==2) # IndexedTable16 |
|
915 { |
|
916 $algorithmAsText='IndexedTable16'; |
|
917 my $nameOfNextOneDirectionIndexedTable16='indexedTable16_'.($outputIsUnicode? 'foreignToUnicode': 'unicodeToForeign').'_'.($#$sourceCodeOfOneDirectionIndexedTables16+2); |
|
918 my $sourceCodeOfNextOneDirectionIndexedTable16=[]; |
|
919 push(@$sourceCodeOfNextOneDirectionIndexedTable16, "LOCAL_D const SCnvConversionData::SOneDirectionData::SRange::UData::SIndexedTable16::SEntry $nameOfNextOneDirectionIndexedTable16\[\]=\n\t\{\n"); |
|
920 my $characterCode; |
|
921 for ($characterCode=$firstInputCharacterCodeInRange; $characterCode<=$lastInputCharacterCodeInRange; ++$characterCode) |
|
922 { |
|
923 if (!defined($characterCodes->{$characterCode})) |
|
924 { |
|
925 die("Error: There is no conversion defined for ".($outputIsUnicode? 'foreign': 'Unicode')." character code ".sprintf("0x%08x", $characterCode)."\n"); |
|
926 } |
|
927 push(@$sourceCodeOfNextOneDirectionIndexedTable16, "\t\t\{\n\t\t".sprintf($formatForOutputCharacters, $characterCodes->{$characterCode})."\n\t\t\}"); |
|
928 if ($characterCode<$lastInputCharacterCodeInRange) |
|
929 { |
|
930 push(@$sourceCodeOfNextOneDirectionIndexedTable16, ','); |
|
931 } |
|
932 push(@$sourceCodeOfNextOneDirectionIndexedTable16, "\n"); |
|
933 delete $characterCodes->{$characterCode}; |
|
934 } |
|
935 push(@$sourceCodeOfNextOneDirectionIndexedTable16, "\t\};\n\n"); |
|
936 push(@$sourceCodeOfOneDirectionIndexedTables16, $sourceCodeOfNextOneDirectionIndexedTable16); |
|
937 $word1="UData_S$algorithmAsText($nameOfNextOneDirectionIndexedTable16)"; |
|
938 } |
|
939 elsif ($algorithm==3) # KeyedTable1616 |
|
940 { |
|
941 $algorithmAsText='KeyedTable1616'; |
|
942 my $nameOfNextOneDirectionKeyedTable1616='keyedTable1616_'.($outputIsUnicode? 'foreignToUnicode': 'unicodeToForeign').'_'.($#$sourceCodeOfOneDirectionKeyedTables1616+2); |
|
943 my $sourceCodeOfNextOneDirectionKeyedTable1616=[]; |
|
944 push(@$sourceCodeOfNextOneDirectionKeyedTable1616, "LOCAL_D const SCnvConversionData::SOneDirectionData::SRange::UData::SKeyedTable1616::SEntry $nameOfNextOneDirectionKeyedTable1616\[\]=\n\t\{\n"); |
|
945 my @characterCodes=grep(($_>=$firstInputCharacterCodeInRange) && ($_<=$lastInputCharacterCodeInRange), sort({$a<=>$b} keys(%$characterCodes))); |
|
946 if (@characterCodes==0) |
|
947 { |
|
948 die("Error: There are no ".($outputIsUnicode? 'foreign': 'Unicode').'-to-'.($outputIsUnicode? 'Unicode': 'foreign')." characters to convert using KeyedTable1616 (range ".sprintf("$formatForInputCharacters-$formatForInputCharacters", $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange).").\n"); |
|
949 } |
|
950 if ($characterCodes[0]!=$firstInputCharacterCodeInRange) |
|
951 { |
|
952 print(STDERR 'Warning: the specified start of the '.($outputIsUnicode? 'foreign': 'Unicode').' range '.sprintf("$formatForInputCharacters-$formatForInputCharacters", $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange).' could actually be '.sprintf("$formatForInputCharacters", $characterCodes[0])."\n"); |
|
953 } |
|
954 if ($characterCodes[-1]!=$lastInputCharacterCodeInRange) |
|
955 { |
|
956 print(STDERR 'Warning: the specified end of the '.($outputIsUnicode? 'foreign': 'Unicode').' range '.sprintf("$formatForInputCharacters-$formatForInputCharacters", $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange).' could actually be '.sprintf("$formatForInputCharacters", $characterCodes[-1])."\n"); |
|
957 } |
|
958 my $characterCode; |
|
959 foreach $characterCode (@characterCodes) |
|
960 { |
|
961 if (defined($characterCodes->{$characterCode})) |
|
962 { |
|
963 push(@$sourceCodeOfNextOneDirectionKeyedTable1616, "\t\t\{\n\t\t".sprintf($formatForInputCharacters, $characterCode).",\n\t\t".sprintf($formatForOutputCharacters, $characterCodes->{$characterCode})."\n\t\t\}"); |
|
964 if ($characterCode<$characterCodes[-1]) |
|
965 { |
|
966 push(@$sourceCodeOfNextOneDirectionKeyedTable1616, ','); |
|
967 } |
|
968 push(@$sourceCodeOfNextOneDirectionKeyedTable1616, "\n"); |
|
969 delete $characterCodes->{$characterCode}; |
|
970 } |
|
971 } |
|
972 push(@$sourceCodeOfNextOneDirectionKeyedTable1616, "\t\};\n\n"); |
|
973 push(@$sourceCodeOfOneDirectionKeyedTables1616, $sourceCodeOfNextOneDirectionKeyedTable1616); |
|
974 $word1="UData_S$algorithmAsText($nameOfNextOneDirectionKeyedTable1616)"; |
|
975 } |
|
976 elsif ($algorithm==4) # KeyedTable16OfIndexedTables16 |
|
977 { |
|
978 $algorithmAsText='KeyedTable16OfIndexedTables16'; |
|
979 my $nameOfNextOneDirectionKeyedTables16OfIndexedTables16_keyedEntries='keyedTables16OfIndexedTables16_keyedEntries_'.($outputIsUnicode? 'foreignToUnicode': 'unicodeToForeign').'_'.($#$sourceCodeOfOneDirectionKeyedTables16OfIndexedTables16_keyedEntries+2); |
|
980 my $sourceCodeOfNextOneDirectionKeyedTables16OfIndexedTables16_keyedEntries=[]; |
|
981 push(@$sourceCodeOfNextOneDirectionKeyedTables16OfIndexedTables16_keyedEntries, "LOCAL_D const SCnvConversionData::SOneDirectionData::SRange::UData::SKeyedTable16OfIndexedTables16::SKeyedEntry $nameOfNextOneDirectionKeyedTables16OfIndexedTables16_keyedEntries\[\]=\n\t\{\n"); |
|
982 my @characterCodes=grep(($_>=$firstInputCharacterCodeInRange) && ($_<=$lastInputCharacterCodeInRange), sort({$a<=>$b} keys(%$characterCodes))); |
|
983 if (@characterCodes==0) |
|
984 { |
|
985 die("Error: There are no ".($outputIsUnicode? 'foreign': 'Unicode').'-to-'.($outputIsUnicode? 'Unicode': 'foreign')." characters to convert using KeyedTable16OfIndexedTables16 (range ".sprintf("$formatForInputCharacters-$formatForInputCharacters", $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange).").\n"); |
|
986 } |
|
987 if ($characterCodes[0]!=$firstInputCharacterCodeInRange) |
|
988 { |
|
989 print(STDERR 'Warning: the specified start of the '.($outputIsUnicode? 'foreign': 'Unicode').' range '.sprintf("$formatForInputCharacters-$formatForInputCharacters", $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange).' could actually be '.sprintf("$formatForInputCharacters", $characterCodes[0])."\n"); |
|
990 } |
|
991 if ($characterCodes[-1]!=$lastInputCharacterCodeInRange) |
|
992 { |
|
993 print(STDERR 'Warning: the specified end of the '.($outputIsUnicode? 'foreign': 'Unicode').' range '.sprintf("$formatForInputCharacters-$formatForInputCharacters", $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange).' could actually be '.sprintf("$formatForInputCharacters", $characterCodes[-1])."\n"); |
|
994 } |
|
995 my @characterCodeRanges=(); |
|
996 my $minimumNumberOfEntriesPerIndexedTable=($parameters ne '')? $parameters: 0; |
|
997 my $firstInputCharacterCodeInIndexedTable=$characterCodes[0]; |
|
998 my $previousCharacterCode=$firstInputCharacterCodeInIndexedTable; |
|
999 my $characterCode; |
|
1000 foreach $characterCode (@characterCodes) |
|
1001 { |
|
1002 ($characterCode>=$previousCharacterCode) or die("Error: internal error 7\n"); |
|
1003 if ($characterCode>$previousCharacterCode+1) |
|
1004 { |
|
1005 if (($previousCharacterCode-$firstInputCharacterCodeInIndexedTable)+1>=$minimumNumberOfEntriesPerIndexedTable) |
|
1006 { |
|
1007 push(@characterCodeRanges, [$firstInputCharacterCodeInIndexedTable, $previousCharacterCode]); |
|
1008 } |
|
1009 $firstInputCharacterCodeInIndexedTable=$characterCode; |
|
1010 } |
|
1011 $previousCharacterCode=$characterCode; |
|
1012 } |
|
1013 push(@characterCodeRanges, [$firstInputCharacterCodeInIndexedTable, $previousCharacterCode]); |
|
1014 @characterCodes=(); |
|
1015 my $characterCodeRange; |
|
1016 foreach $characterCodeRange (@characterCodeRanges) |
|
1017 { |
|
1018 my $nameOfNextOneDirectionKeyedTables16OfIndexedTables16_indexedEntries='keyedTables16OfIndexedTables16_indexedEntries_'.($outputIsUnicode? 'foreignToUnicode': 'unicodeToForeign').'_'.($#$sourceCodeOfOneDirectionKeyedTables16OfIndexedTables16_indexedEntries+2); |
|
1019 my $sourceCodeOfNextOneDirectionKeyedTables16OfIndexedTables16_indexedEntries=[]; |
|
1020 push(@$sourceCodeOfNextOneDirectionKeyedTables16OfIndexedTables16_indexedEntries, "LOCAL_D const TUint16 $nameOfNextOneDirectionKeyedTables16OfIndexedTables16_indexedEntries\[\]=\n\t\{\n"); |
|
1021 my $characterCode; |
|
1022 my $lastInputCharacterCodeInIndexedTable=$characterCodeRange->[1]; |
|
1023 for ($characterCode=$characterCodeRange->[0]; $characterCode<=$lastInputCharacterCodeInIndexedTable; ++$characterCode) |
|
1024 { |
|
1025 if (!defined($characterCodes->{$characterCode})) |
|
1026 { |
|
1027 die("Error: internal error 8\n"); |
|
1028 } |
|
1029 push(@$sourceCodeOfNextOneDirectionKeyedTables16OfIndexedTables16_indexedEntries, "\t".sprintf($formatForOutputCharacters, $characterCodes->{$characterCode})); |
|
1030 if ($characterCode<$lastInputCharacterCodeInIndexedTable) |
|
1031 { |
|
1032 push(@$sourceCodeOfNextOneDirectionKeyedTables16OfIndexedTables16_indexedEntries, ','); |
|
1033 } |
|
1034 push(@$sourceCodeOfNextOneDirectionKeyedTables16OfIndexedTables16_indexedEntries, "\n"); |
|
1035 delete $characterCodes->{$characterCode}; |
|
1036 } |
|
1037 push(@$sourceCodeOfNextOneDirectionKeyedTables16OfIndexedTables16_indexedEntries, "\t\};\n\n"); |
|
1038 push(@$sourceCodeOfOneDirectionKeyedTables16OfIndexedTables16_indexedEntries, $sourceCodeOfNextOneDirectionKeyedTables16OfIndexedTables16_indexedEntries); |
|
1039 push(@$sourceCodeOfNextOneDirectionKeyedTables16OfIndexedTables16_keyedEntries, "\t\t\{\n\t\t".sprintf($formatForInputCharacters, $characterCodeRange->[0]).",\n\t\t".sprintf($formatForInputCharacters, $characterCodeRange->[1]).",\n\t\t$nameOfNextOneDirectionKeyedTables16OfIndexedTables16_indexedEntries\n\t\t\}"); |
|
1040 if ($characterCodeRange->[1]<$characterCodeRanges[-1]->[1]) |
|
1041 { |
|
1042 push(@$sourceCodeOfNextOneDirectionKeyedTables16OfIndexedTables16_keyedEntries, ','); |
|
1043 } |
|
1044 push(@$sourceCodeOfNextOneDirectionKeyedTables16OfIndexedTables16_keyedEntries, "\n"); |
|
1045 } |
|
1046 push(@$sourceCodeOfNextOneDirectionKeyedTables16OfIndexedTables16_keyedEntries, "\t\};\n\n"); |
|
1047 push(@$sourceCodeOfOneDirectionKeyedTables16OfIndexedTables16_keyedEntries, $sourceCodeOfNextOneDirectionKeyedTables16OfIndexedTables16_keyedEntries); |
|
1048 $word1="UData_S$algorithmAsText($nameOfNextOneDirectionKeyedTables16OfIndexedTables16_keyedEntries)"; |
|
1049 } |
|
1050 elsif ($algorithm==5) # IndexedTable32 |
|
1051 { |
|
1052 $algorithmAsText='IndexedTable32'; |
|
1053 my $nameOfNextOneDirectionIndexedTable32='indexedTable32_'.($outputIsUnicode? 'foreignToUnicode': 'unicodeToForeign').'_'.($#$sourceCodeOfOneDirectionIndexedTables32+2); |
|
1054 my $sourceCodeOfNextOneDirectionIndexedTable32=[]; |
|
1055 push(@$sourceCodeOfNextOneDirectionIndexedTable32, "LOCAL_D const SCnvConversionData::SOneDirectionData::SRange::UData::SIndexedTable32::SEntry $nameOfNextOneDirectionIndexedTable32\[\]=\n\t\{\n"); |
|
1056 my $characterCode; |
|
1057 for ($characterCode=$firstInputCharacterCodeInRange; $characterCode<=$lastInputCharacterCodeInRange; ++$characterCode) |
|
1058 { |
|
1059 if (!defined($characterCodes->{$characterCode})) |
|
1060 { |
|
1061 die("Error: There is no conversion defined for ".($outputIsUnicode? 'foreign': 'Unicode')." character code ".sprintf("0x%08x", $characterCode)."\n"); |
|
1062 } |
|
1063 push(@$sourceCodeOfNextOneDirectionIndexedTable32, "\t\t\{\n\t\t".sprintf($formatForOutputCharacters, $characterCodes->{$characterCode})."\n\t\t\}"); |
|
1064 if ($characterCode<$lastInputCharacterCodeInRange) |
|
1065 { |
|
1066 push(@$sourceCodeOfNextOneDirectionIndexedTable32, ','); |
|
1067 } |
|
1068 push(@$sourceCodeOfNextOneDirectionIndexedTable32, "\n"); |
|
1069 delete $characterCodes->{$characterCode}; |
|
1070 } |
|
1071 push(@$sourceCodeOfNextOneDirectionIndexedTable32, "\t\};\n\n"); |
|
1072 push(@$sourceCodeOfOneDirectionIndexedTables32, $sourceCodeOfNextOneDirectionIndexedTable32); |
|
1073 $word1="UData_S$algorithmAsText($nameOfNextOneDirectionIndexedTable32)"; |
|
1074 } |
|
1075 elsif ($algorithm==6) # KeyedTable3232 |
|
1076 { |
|
1077 $algorithmAsText='KeyedTable3232'; |
|
1078 my $nameOfNextOneDirectionKeyedTable3232='keyedTable3232_'.($outputIsUnicode? 'foreignToUnicode': 'unicodeToForeign').'_'.($#$sourceCodeOfOneDirectionKeyedTables3232+2); |
|
1079 my $sourceCodeOfNextOneDirectionKeyedTable3232=[]; |
|
1080 push(@$sourceCodeOfNextOneDirectionKeyedTable3232, "LOCAL_D const SCnvConversionData::SOneDirectionData::SRange::UData::SKeyedTable3232::SEntry $nameOfNextOneDirectionKeyedTable3232\[\]=\n\t\{\n"); |
|
1081 my @characterCodes=grep(($_>=$firstInputCharacterCodeInRange) && ($_<=$lastInputCharacterCodeInRange), sort({$a<=>$b} keys(%$characterCodes))); |
|
1082 if (@characterCodes==0) |
|
1083 { |
|
1084 die("Error: There are no ".($outputIsUnicode? 'foreign': 'Unicode').'-to-'.($outputIsUnicode? 'Unicode': 'foreign')." characters to convert using KeyedTable3232 (range ".sprintf("$formatForInputCharacters-$formatForInputCharacters", $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange).").\n"); |
|
1085 } |
|
1086 if ($characterCodes[0]!=$firstInputCharacterCodeInRange) |
|
1087 { |
|
1088 print(STDERR 'Warning: the specified start of the '.($outputIsUnicode? 'foreign': 'Unicode').' range '.sprintf("$formatForInputCharacters-$formatForInputCharacters", $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange).' could actually be '.sprintf($formatForInputCharacters, $characterCodes[0])."\n"); |
|
1089 } |
|
1090 if ($characterCodes[-1]!=$lastInputCharacterCodeInRange) |
|
1091 { |
|
1092 print(STDERR 'Warning: the specified end of the '.($outputIsUnicode? 'foreign': 'Unicode').' range '.sprintf("$formatForInputCharacters-$formatForInputCharacters", $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange).' could actually be '.sprintf($formatForInputCharacters, $characterCodes[-1])."\n"); |
|
1093 } |
|
1094 my $characterCode; |
|
1095 foreach $characterCode (@characterCodes) |
|
1096 { |
|
1097 if (defined($characterCodes->{$characterCode})) |
|
1098 { |
|
1099 push(@$sourceCodeOfNextOneDirectionKeyedTable3232, "\t\t\{\n\t\t".sprintf($formatForInputCharacters, $characterCode).",\n\t\t".sprintf($formatForOutputCharacters, $characterCodes->{$characterCode})."\n\t\t\}"); |
|
1100 if ($characterCode<$characterCodes[-1]) |
|
1101 { |
|
1102 push(@$sourceCodeOfNextOneDirectionKeyedTable3232, ','); |
|
1103 } |
|
1104 push(@$sourceCodeOfNextOneDirectionKeyedTable3232, "\n"); |
|
1105 delete $characterCodes->{$characterCode}; |
|
1106 } |
|
1107 } |
|
1108 push(@$sourceCodeOfNextOneDirectionKeyedTable3232, "\t\};\n\n"); |
|
1109 push(@$sourceCodeOfOneDirectionKeyedTables3232, $sourceCodeOfNextOneDirectionKeyedTable3232); |
|
1110 $word1="UData_S$algorithmAsText($nameOfNextOneDirectionKeyedTable3232)"; |
|
1111 } |
|
1112 elsif ($algorithm==7) # KeyedTable32OfIndexedTables32 |
|
1113 { |
|
1114 $algorithmAsText='KeyedTable32OfIndexedTables32'; |
|
1115 my $nameOfNextOneDirectionKeyedTables32OfIndexedTables32_keyedEntries='keyedTables32OfIndexedTables32_keyedEntries_'.($outputIsUnicode? 'foreignToUnicode': 'unicodeToForeign').'_'.($#$sourceCodeOfOneDirectionKeyedTables32OfIndexedTables32_keyedEntries+2); |
|
1116 my $sourceCodeOfNextOneDirectionKeyedTables32OfIndexedTables32_keyedEntries=[]; |
|
1117 push(@$sourceCodeOfNextOneDirectionKeyedTables32OfIndexedTables32_keyedEntries, "LOCAL_D const SCnvConversionData::SOneDirectionData::SRange::UData::SKeyedTable32OfIndexedTables32::SKeyedEntry $nameOfNextOneDirectionKeyedTables32OfIndexedTables32_keyedEntries\[\]=\n\t\{\n"); |
|
1118 my @characterCodes=grep(($_>=$firstInputCharacterCodeInRange) && ($_<=$lastInputCharacterCodeInRange), sort({$a<=>$b} keys(%$characterCodes))); |
|
1119 if (@characterCodes==0) |
|
1120 { |
|
1121 die("Error: There are no ".($outputIsUnicode? 'foreign': 'Unicode').'-to-'.($outputIsUnicode? 'Unicode': 'foreign')." characters to convert using KeyedTable32OfIndexedTables32 (range ".sprintf("$formatForInputCharacters-$formatForInputCharacters", $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange).").\n"); |
|
1122 } |
|
1123 if ($characterCodes[0]!=$firstInputCharacterCodeInRange) |
|
1124 { |
|
1125 print(STDERR 'Warning: the specified start of the '.($outputIsUnicode? 'foreign': 'Unicode').' range '.sprintf("$formatForInputCharacters-$formatForInputCharacters", $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange).' could actually be '.sprintf("$formatForInputCharacters", $characterCodes[0])."\n"); |
|
1126 } |
|
1127 if ($characterCodes[-1]!=$lastInputCharacterCodeInRange) |
|
1128 { |
|
1129 print(STDERR 'Warning: the specified end of the '.($outputIsUnicode? 'foreign': 'Unicode').' range '.sprintf("$formatForInputCharacters-$formatForInputCharacters", $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange).' could actually be '.sprintf("$formatForInputCharacters", $characterCodes[-1])."\n"); |
|
1130 } |
|
1131 my @characterCodeRanges=(); |
|
1132 my $minimumNumberOfEntriesPerIndexedTable=($parameters ne '')? $parameters: 0; |
|
1133 my $firstInputCharacterCodeInIndexedTable=$characterCodes[0]; |
|
1134 my $previousCharacterCode=$firstInputCharacterCodeInIndexedTable; |
|
1135 my $characterCode; |
|
1136 foreach $characterCode (@characterCodes) |
|
1137 { |
|
1138 ($characterCode>=$previousCharacterCode) or die("Error: internal error 7\n"); |
|
1139 if ($characterCode>$previousCharacterCode+1) |
|
1140 { |
|
1141 if (($previousCharacterCode-$firstInputCharacterCodeInIndexedTable)+1>=$minimumNumberOfEntriesPerIndexedTable) |
|
1142 { |
|
1143 push(@characterCodeRanges, [$firstInputCharacterCodeInIndexedTable, $previousCharacterCode]); |
|
1144 } |
|
1145 $firstInputCharacterCodeInIndexedTable=$characterCode; |
|
1146 } |
|
1147 $previousCharacterCode=$characterCode; |
|
1148 } |
|
1149 push(@characterCodeRanges, [$firstInputCharacterCodeInIndexedTable, $previousCharacterCode]); |
|
1150 @characterCodes=(); |
|
1151 my $characterCodeRange; |
|
1152 foreach $characterCodeRange (@characterCodeRanges) |
|
1153 { |
|
1154 my $nameOfNextOneDirectionKeyedTables32OfIndexedTables32_indexedEntries='keyedTables32OfIndexedTables32_indexedEntries_'.($outputIsUnicode? 'foreignToUnicode': 'unicodeToForeign').'_'.($#$sourceCodeOfOneDirectionKeyedTables32OfIndexedTables32_indexedEntries+2); |
|
1155 my $sourceCodeOfNextOneDirectionKeyedTables32OfIndexedTables32_indexedEntries=[]; |
|
1156 push(@$sourceCodeOfNextOneDirectionKeyedTables32OfIndexedTables32_indexedEntries, "LOCAL_D const TUint32 $nameOfNextOneDirectionKeyedTables32OfIndexedTables32_indexedEntries\[\]=\n\t\{\n"); |
|
1157 my $characterCode; |
|
1158 my $lastInputCharacterCodeInIndexedTable=$characterCodeRange->[1]; |
|
1159 for ($characterCode=$characterCodeRange->[0]; $characterCode<=$lastInputCharacterCodeInIndexedTable; ++$characterCode) |
|
1160 { |
|
1161 if (!defined($characterCodes->{$characterCode})) |
|
1162 { |
|
1163 die("Error: internal error 8\n"); |
|
1164 } |
|
1165 push(@$sourceCodeOfNextOneDirectionKeyedTables32OfIndexedTables32_indexedEntries, "\t".sprintf($formatForOutputCharacters, $characterCodes->{$characterCode})); |
|
1166 if ($characterCode<$lastInputCharacterCodeInIndexedTable) |
|
1167 { |
|
1168 push(@$sourceCodeOfNextOneDirectionKeyedTables32OfIndexedTables32_indexedEntries, ','); |
|
1169 } |
|
1170 push(@$sourceCodeOfNextOneDirectionKeyedTables32OfIndexedTables32_indexedEntries, "\n"); |
|
1171 delete $characterCodes->{$characterCode}; |
|
1172 } |
|
1173 push(@$sourceCodeOfNextOneDirectionKeyedTables32OfIndexedTables32_indexedEntries, "\t\};\n\n"); |
|
1174 push(@$sourceCodeOfOneDirectionKeyedTables32OfIndexedTables32_indexedEntries, $sourceCodeOfNextOneDirectionKeyedTables32OfIndexedTables32_indexedEntries); |
|
1175 push(@$sourceCodeOfNextOneDirectionKeyedTables32OfIndexedTables32_keyedEntries, "\t\t\{\n\t\t".sprintf($formatForInputCharacters, $characterCodeRange->[0]).",\n\t\t".sprintf($formatForInputCharacters, $characterCodeRange->[1]).",\n\t\t$nameOfNextOneDirectionKeyedTables32OfIndexedTables32_indexedEntries\n\t\t\}"); |
|
1176 if ($characterCodeRange->[1]<$characterCodeRanges[-1]->[1]) |
|
1177 { |
|
1178 push(@$sourceCodeOfNextOneDirectionKeyedTables32OfIndexedTables32_keyedEntries, ','); |
|
1179 } |
|
1180 push(@$sourceCodeOfNextOneDirectionKeyedTables32OfIndexedTables32_keyedEntries, "\n"); |
|
1181 } |
|
1182 push(@$sourceCodeOfNextOneDirectionKeyedTables32OfIndexedTables32_keyedEntries, "\t\};\n\n"); |
|
1183 push(@$sourceCodeOfOneDirectionKeyedTables32OfIndexedTables32_keyedEntries, $sourceCodeOfNextOneDirectionKeyedTables32OfIndexedTables32_keyedEntries); |
|
1184 $word1="UData_S$algorithmAsText($nameOfNextOneDirectionKeyedTables32OfIndexedTables32_keyedEntries)"; |
|
1185 } |
|
1186 else |
|
1187 { |
|
1188 die("Error: internal error 9\n"); |
|
1189 } |
|
1190 push(@$sourceCodeOfTopLevelStructures, "\t\t\{\n\t\t".sprintf($formatForInputCharacters, $firstInputCharacterCodeInRange).",\n\t\t".sprintf($formatForInputCharacters, $lastInputCharacterCodeInRange).",\n\t\tSCnvConversionData::SOneDirectionData::SRange::E$algorithmAsText,\n\t\t".$sizeOfOutputCharacterCodeInBytesIfForeign.",\n\t\t0,\n\t\t\t\{\n\t\t\t".$word1."\n\t\t\t\}\n\t\t\}"); |
|
1191 if ($i<$indexOfLastRange) |
|
1192 { |
|
1193 push(@$sourceCodeOfTopLevelStructures, ','); |
|
1194 } |
|
1195 push(@$sourceCodeOfTopLevelStructures, "\n"); |
|
1196 } |
|
1197 my @characterCodes=sort({$a<=>$b} keys(%$characterCodes)); |
|
1198 if (@characterCodes>0) |
|
1199 { |
|
1200 die('The following '.($outputIsUnicode? 'foreign': 'Unicode').' characters have no conversion algorithm specified: ['.join(', ', map(sprintf($formatForInputCharacters, $_), @characterCodes))."\]\n"); |
|
1201 } |
|
1202 push(@$sourceCodeOfTopLevelStructures, "\t\};\n\n"); |
|
1203 } |
|
1204 |
|
1205 sub writeSourceCodeFinalStuff |
|
1206 { |
|
1207 my $fileHandle=shift; |
|
1208 my $sourceCodeOfForeignToUnicodeIndexedTables16=shift; |
|
1209 my $sourceCodeOfForeignToUnicodeKeyedTables1616=shift; |
|
1210 my $sourceCodeOfForeignToUnicodeKeyedTables16OfIndexedTables16_indexedEntries=shift; |
|
1211 my $sourceCodeOfForeignToUnicodeKeyedTables16OfIndexedTables16_keyedEntries=shift; |
|
1212 my $sourceCodeOfUnicodeToForeignIndexedTables16=shift; |
|
1213 my $sourceCodeOfUnicodeToForeignKeyedTables1616=shift; |
|
1214 my $sourceCodeOfUnicodeToForeignKeyedTables16OfIndexedTables16_indexedEntries=shift; |
|
1215 my $sourceCodeOfUnicodeToForeignKeyedTables16OfIndexedTables16_keyedEntries=shift; |
|
1216 |
|
1217 my $sourceCodeOfForeignToUnicodeIndexedTables32=shift; |
|
1218 my $sourceCodeOfForeignToUnicodeKeyedTables3232=shift; |
|
1219 my $sourceCodeOfForeignToUnicodeKeyedTables32OfIndexedTables32_indexedEntries=shift; |
|
1220 my $sourceCodeOfForeignToUnicodeKeyedTables32OfIndexedTables32_keyedEntries=shift; |
|
1221 my $sourceCodeOfUnicodeToForeignIndexedTables32=shift; |
|
1222 my $sourceCodeOfUnicodeToForeignKeyedTables3232=shift; |
|
1223 my $sourceCodeOfUnicodeToForeignKeyedTables32OfIndexedTables32_indexedEntries=shift; |
|
1224 my $sourceCodeOfUnicodeToForeignKeyedTables32OfIndexedTables32_keyedEntries=shift; |
|
1225 |
|
1226 my $sourceCodeOfTopLevelStructures=shift; |
|
1227 my $endiannessAsText=shift; |
|
1228 my $additionalSubsetTables=shift; |
|
1229 my $sourceCodeChunk; |
|
1230 my $arrayOfSourceCodeChunks; |
|
1231 |
|
1232 foreach $arrayOfSourceCodeChunks (@$sourceCodeOfForeignToUnicodeIndexedTables16) |
|
1233 { |
|
1234 foreach $sourceCodeChunk (@$arrayOfSourceCodeChunks) |
|
1235 { |
|
1236 print($fileHandle $sourceCodeChunk); |
|
1237 } |
|
1238 } |
|
1239 foreach $arrayOfSourceCodeChunks (@$sourceCodeOfForeignToUnicodeKeyedTables1616) |
|
1240 { |
|
1241 foreach $sourceCodeChunk (@$arrayOfSourceCodeChunks) |
|
1242 { |
|
1243 print($fileHandle $sourceCodeChunk); |
|
1244 } |
|
1245 } |
|
1246 foreach $arrayOfSourceCodeChunks (@$sourceCodeOfForeignToUnicodeKeyedTables16OfIndexedTables16_indexedEntries) |
|
1247 { |
|
1248 foreach $sourceCodeChunk (@$arrayOfSourceCodeChunks) |
|
1249 { |
|
1250 print($fileHandle $sourceCodeChunk); |
|
1251 } |
|
1252 } |
|
1253 foreach $arrayOfSourceCodeChunks (@$sourceCodeOfForeignToUnicodeKeyedTables16OfIndexedTables16_keyedEntries) |
|
1254 { |
|
1255 foreach $sourceCodeChunk (@$arrayOfSourceCodeChunks) |
|
1256 { |
|
1257 print($fileHandle $sourceCodeChunk); |
|
1258 } |
|
1259 } |
|
1260 foreach $arrayOfSourceCodeChunks (@$sourceCodeOfUnicodeToForeignIndexedTables16) |
|
1261 { |
|
1262 foreach $sourceCodeChunk (@$arrayOfSourceCodeChunks) |
|
1263 { |
|
1264 print($fileHandle $sourceCodeChunk); |
|
1265 } |
|
1266 } |
|
1267 foreach $arrayOfSourceCodeChunks (@$sourceCodeOfUnicodeToForeignKeyedTables1616) |
|
1268 { |
|
1269 foreach $sourceCodeChunk (@$arrayOfSourceCodeChunks) |
|
1270 { |
|
1271 print($fileHandle $sourceCodeChunk); |
|
1272 } |
|
1273 } |
|
1274 foreach $arrayOfSourceCodeChunks (@$sourceCodeOfUnicodeToForeignKeyedTables16OfIndexedTables16_indexedEntries) |
|
1275 { |
|
1276 foreach $sourceCodeChunk (@$arrayOfSourceCodeChunks) |
|
1277 { |
|
1278 print($fileHandle $sourceCodeChunk); |
|
1279 } |
|
1280 } |
|
1281 foreach $arrayOfSourceCodeChunks (@$sourceCodeOfUnicodeToForeignKeyedTables16OfIndexedTables16_keyedEntries) |
|
1282 { |
|
1283 foreach $sourceCodeChunk (@$arrayOfSourceCodeChunks) |
|
1284 { |
|
1285 print($fileHandle $sourceCodeChunk); |
|
1286 } |
|
1287 } |
|
1288 # for 32 bit encoding begin |
|
1289 foreach $arrayOfSourceCodeChunks (@$sourceCodeOfForeignToUnicodeIndexedTables32) |
|
1290 { |
|
1291 foreach $sourceCodeChunk (@$arrayOfSourceCodeChunks) |
|
1292 { |
|
1293 print($fileHandle $sourceCodeChunk); |
|
1294 } |
|
1295 } |
|
1296 foreach $arrayOfSourceCodeChunks (@$sourceCodeOfForeignToUnicodeKeyedTables3232) |
|
1297 { |
|
1298 foreach $sourceCodeChunk (@$arrayOfSourceCodeChunks) |
|
1299 { |
|
1300 print($fileHandle $sourceCodeChunk); |
|
1301 } |
|
1302 } |
|
1303 foreach $arrayOfSourceCodeChunks (@$sourceCodeOfForeignToUnicodeKeyedTables32OfIndexedTables32_indexedEntries) |
|
1304 { |
|
1305 foreach $sourceCodeChunk (@$arrayOfSourceCodeChunks) |
|
1306 { |
|
1307 print($fileHandle $sourceCodeChunk); |
|
1308 } |
|
1309 } |
|
1310 foreach $arrayOfSourceCodeChunks (@$sourceCodeOfForeignToUnicodeKeyedTables32OfIndexedTables32_keyedEntries) |
|
1311 { |
|
1312 foreach $sourceCodeChunk (@$arrayOfSourceCodeChunks) |
|
1313 { |
|
1314 print($fileHandle $sourceCodeChunk); |
|
1315 } |
|
1316 } |
|
1317 foreach $arrayOfSourceCodeChunks (@$sourceCodeOfUnicodeToForeignIndexedTables32) |
|
1318 { |
|
1319 foreach $sourceCodeChunk (@$arrayOfSourceCodeChunks) |
|
1320 { |
|
1321 print($fileHandle $sourceCodeChunk); |
|
1322 } |
|
1323 } |
|
1324 foreach $arrayOfSourceCodeChunks (@$sourceCodeOfUnicodeToForeignKeyedTables3232) |
|
1325 { |
|
1326 foreach $sourceCodeChunk (@$arrayOfSourceCodeChunks) |
|
1327 { |
|
1328 print($fileHandle $sourceCodeChunk); |
|
1329 } |
|
1330 } |
|
1331 foreach $arrayOfSourceCodeChunks (@$sourceCodeOfUnicodeToForeignKeyedTables32OfIndexedTables32_indexedEntries) |
|
1332 { |
|
1333 foreach $sourceCodeChunk (@$arrayOfSourceCodeChunks) |
|
1334 { |
|
1335 print($fileHandle $sourceCodeChunk); |
|
1336 } |
|
1337 } |
|
1338 foreach $arrayOfSourceCodeChunks (@$sourceCodeOfUnicodeToForeignKeyedTables32OfIndexedTables32_keyedEntries) |
|
1339 { |
|
1340 foreach $sourceCodeChunk (@$arrayOfSourceCodeChunks) |
|
1341 { |
|
1342 print($fileHandle $sourceCodeChunk); |
|
1343 } |
|
1344 } |
|
1345 # for 32 bit encoding end |
|
1346 foreach $sourceCodeChunk (@$sourceCodeOfTopLevelStructures) |
|
1347 { |
|
1348 print($fileHandle $sourceCodeChunk); |
|
1349 } |
|
1350 |
|
1351 print($fileHandle "GLDEF_D const SCnvConversionData conversionData=\n\t\{\n\tSCnvConversionData::E$endiannessAsText,\n\t\t\{\n\t\tARRAY_LENGTH(foreignVariableByteDataRanges),\n\t\tforeignVariableByteDataRanges\n\t\t\},\n\t\t\{\n\t\tARRAY_LENGTH(foreignToUnicodeDataRanges),\n\t\tforeignToUnicodeDataRanges\n\t\t\},\n\t\t\{\n\t\tARRAY_LENGTH(unicodeToForeignDataRanges),\n\t\tunicodeToForeignDataRanges\n\t\t\},\n\tNULL,\n\tNULL\n\t\};\n\n"); |
|
1352 |
|
1353 my $additionalSubsetTableName; |
|
1354 my $additionalSubsetTableData; |
|
1355 while (($additionalSubsetTableName, $additionalSubsetTableData)=each(%$additionalSubsetTables)) |
|
1356 { |
|
1357 (defined($additionalSubsetTableData->[0]) && defined($additionalSubsetTableData->[1]) && defined($additionalSubsetTableData->[2]) && defined($additionalSubsetTableData->[3])) or die("Error: incomplete definition of \"$additionalSubsetTableName\"\n"); |
|
1358 print($fileHandle "GLREF_D const SCnvConversionData $additionalSubsetTableName;\n"); |
|
1359 print($fileHandle "GLDEF_D const SCnvConversionData $additionalSubsetTableName=\n\t\{\n\tSCnvConversionData::E$endiannessAsText,\n\t\t\{\n\t\tARRAY_LENGTH(foreignVariableByteDataRanges),\n\t\tforeignVariableByteDataRanges\n\t\t\},\n\t\t\{\n\t\t$additionalSubsetTableData->[1]-$additionalSubsetTableData->[0],\n\t\tforeignToUnicodeDataRanges+$additionalSubsetTableData->[0]\n\t\t\},\n\t\t\{\n\t\t$additionalSubsetTableData->[3]-$additionalSubsetTableData->[2],\n\t\tunicodeToForeignDataRanges+$additionalSubsetTableData->[2]\n\t\t\}\n\t\};\n\n"); |
|
1360 } |
|
1361 } |
|
1362 |
|
1363 sub writeBinaryHeader |
|
1364 { |
|
1365 my $fileHandle=shift; |
|
1366 my $uid=shift; |
|
1367 my $endianness=shift; |
|
1368 my $replacementForUnconvertibleUnicodeCharacters=shift; |
|
1369 &writeUids($fileHandle, 0x100011bd, $uid, 0); |
|
1370 &write32($fileHandle, 1); # version number of the file format |
|
1371 &write32($fileHandle, 0); # not currently used |
|
1372 &write8($fileHandle, 0); # number of Unicode characters in the name (which is now derived from the file-name, hence why this is zero) |
|
1373 &write8($fileHandle, $endianness); |
|
1374 &write8($fileHandle, length($replacementForUnconvertibleUnicodeCharacters)); |
|
1375 &writeString($fileHandle, $replacementForUnconvertibleUnicodeCharacters); |
|
1376 } |
|
1377 |
|
1378 sub writeBinaryForeignVariableByteData |
|
1379 { |
|
1380 my $fileHandle=shift; |
|
1381 my $foreignVariableByteData=shift; |
|
1382 &writePositiveIntegerCompacted30($fileHandle, scalar(@$foreignVariableByteData)); |
|
1383 my $rangeData; |
|
1384 foreach $rangeData (@$foreignVariableByteData) |
|
1385 { |
|
1386 if (@$rangeData!=3) |
|
1387 { |
|
1388 die("Error: internal error 10\n"); |
|
1389 } |
|
1390 my $firstInitialByteValueInRange=$rangeData->[0]; |
|
1391 my $lastInitialByteValueInRange=$rangeData->[1]; |
|
1392 if ($lastInitialByteValueInRange<$firstInitialByteValueInRange) |
|
1393 { |
|
1394 die("Error: internal error 11\n"); |
|
1395 } |
|
1396 &write8($fileHandle, $firstInitialByteValueInRange); |
|
1397 &write8($fileHandle, $lastInitialByteValueInRange); |
|
1398 &write8($fileHandle, $rangeData->[2]); # numberOfSubsequentBytes |
|
1399 } |
|
1400 } |
|
1401 |
|
1402 sub writeBinaryOneDirectionData |
|
1403 { |
|
1404 my $fileHandle=shift; |
|
1405 my $oneDirectionData=shift; |
|
1406 my $characterCodes=shift; |
|
1407 my $outputIsUnicode=shift; |
|
1408 &writePositiveIntegerCompacted30($fileHandle, scalar(@$oneDirectionData)); |
|
1409 my $rangeData; |
|
1410 foreach $rangeData (@$oneDirectionData) |
|
1411 { |
|
1412 ## $rangeData is $includePriority, $searchPriority, $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange, $algorithm[, $sizeOfOutputCharacterCodeInBytes], $parameters |
|
1413 if (scalar(@$rangeData)!=($outputIsUnicode? 6: 7)) |
|
1414 { |
|
1415 die("Error: internal error 12\n"); |
|
1416 } |
|
1417 my $firstInputCharacterCodeInRange=$rangeData->[2]; |
|
1418 my $lastInputCharacterCodeInRange=$rangeData->[3]; |
|
1419 if ($lastInputCharacterCodeInRange<$firstInputCharacterCodeInRange) |
|
1420 { |
|
1421 die("Error: internal error 13\n"); |
|
1422 } |
|
1423 &writePositiveIntegerCompacted30($fileHandle, $firstInputCharacterCodeInRange); |
|
1424 &writePositiveIntegerCompacted30($fileHandle, $lastInputCharacterCodeInRange); |
|
1425 my $algorithm=$rangeData->[4]; |
|
1426 &write8($fileHandle, $algorithm); |
|
1427 if (!$outputIsUnicode) |
|
1428 { |
|
1429 &write8($fileHandle, $rangeData->[5]); # sizeOfOutputCharacterCodeInBytesIfForeign |
|
1430 } |
|
1431 if ($algorithm==0) # Direct |
|
1432 { |
|
1433 my $characterCode; |
|
1434 for ($characterCode=$firstInputCharacterCodeInRange; $characterCode<=$lastInputCharacterCodeInRange; ++$characterCode) |
|
1435 { |
|
1436 if (!defined($characterCodes->{$characterCode})) |
|
1437 { |
|
1438 die("Error: There is no conversion defined for ".($outputIsUnicode? 'foreign': 'Unicode')." character code ".sprintf("0x%08x", $characterCode)."\n"); |
|
1439 } |
|
1440 if ($characterCodes->{$characterCode}!=$characterCode) |
|
1441 { |
|
1442 die("Error: the conversion from ".($outputIsUnicode? 'foreign': 'Unicode')." character code ".sprintf("0x%08x", $characterCode)." to ".($outputIsUnicode? 'Unicode': 'foreign')." character code ".sprintf("0x%08x", $characterCodes->{$characterCode})." is not a direct conversion\n"); |
|
1443 } |
|
1444 delete $characterCodes->{$characterCode}; |
|
1445 } |
|
1446 } |
|
1447 elsif ($algorithm==1) # Offset |
|
1448 { |
|
1449 my $offset=$characterCodes->{$firstInputCharacterCodeInRange}-$firstInputCharacterCodeInRange; |
|
1450 delete $characterCodes->{$firstInputCharacterCodeInRange}; |
|
1451 my $characterCode; |
|
1452 for ($characterCode=$firstInputCharacterCodeInRange+1; $characterCode<=$lastInputCharacterCodeInRange; ++$characterCode) |
|
1453 { |
|
1454 if (!defined($characterCodes->{$characterCode})) |
|
1455 { |
|
1456 die("Error: There is no conversion defined for ".($outputIsUnicode? 'foreign': 'Unicode')." character code ".sprintf("0x%08x (0x%08x-0x%08x)", $characterCode, $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange)."\n"); |
|
1457 } |
|
1458 if ($characterCodes->{$characterCode}-$characterCode!=$offset) |
|
1459 { |
|
1460 die("Error: the conversion from ".($outputIsUnicode? 'foreign': 'Unicode')." character code ".sprintf("0x%08x", $characterCode)." to ".($outputIsUnicode? 'Unicode': 'foreign')." character code ".sprintf("0x%08x", $characterCodes->{$characterCode})." has a different offset from the previous one in the range\n"); |
|
1461 } |
|
1462 delete $characterCodes->{$characterCode}; |
|
1463 } |
|
1464 &writeSignedIntegerCompacted29($fileHandle, $offset); |
|
1465 } |
|
1466 elsif ($algorithm==2) # IndexedTable16 |
|
1467 { |
|
1468 my $characterCode; |
|
1469 for ($characterCode=$firstInputCharacterCodeInRange; $characterCode<=$lastInputCharacterCodeInRange; ++$characterCode) |
|
1470 { |
|
1471 if (!defined($characterCodes->{$characterCode})) |
|
1472 { |
|
1473 die("Error: There is no conversion defined for ".($outputIsUnicode? 'foreign': 'Unicode')." character code ".sprintf("0x%08x", $characterCode)."\n"); |
|
1474 } |
|
1475 &write16($fileHandle, $characterCodes->{$characterCode}); |
|
1476 delete $characterCodes->{$characterCode}; |
|
1477 } |
|
1478 } |
|
1479 elsif ($algorithm==3) # KeyedTable1616 |
|
1480 { |
|
1481 my $characterCode; |
|
1482 my @table=(); |
|
1483 for ($characterCode=$firstInputCharacterCodeInRange; $characterCode<=$lastInputCharacterCodeInRange; ++$characterCode) |
|
1484 { |
|
1485 if (defined($characterCodes->{$characterCode})) |
|
1486 { |
|
1487 push(@table, [$characterCode, $characterCodes->{$characterCode}]); |
|
1488 delete $characterCodes->{$characterCode}; |
|
1489 } |
|
1490 } |
|
1491 my $firstIteration=1; |
|
1492 my $lastKey; |
|
1493 &writePositiveIntegerCompacted30($fileHandle, scalar(@table)); |
|
1494 if ($table[0][0]!=$firstInputCharacterCodeInRange) |
|
1495 { |
|
1496 die("Error: no conversion is specified for the first ".($outputIsUnicode? 'foreign': 'Unicode')." character code in the KeyedTable1616 range ".sprintf("0x%08x to 0x%08x", $firstInputCharacterCodeInRange, $lastInputCharacterCodeInRange)."\n"); |
|
1497 } |
|
1498 my $pair; |
|
1499 foreach $pair (@table) |
|
1500 { |
|
1501 my $key=$pair->[0]; |
|
1502 if ($firstIteration) |
|
1503 { |
|
1504 $firstIteration=0; |
|
1505 } |
|
1506 else |
|
1507 { |
|
1508 if ($key<=$lastKey) |
|
1509 { |
|
1510 die("Error: internal error 14\n"); |
|
1511 } |
|
1512 &writePositiveIntegerCompacted15($fileHandle, $key-$lastKey); |
|
1513 } |
|
1514 &write16($fileHandle, $pair->[1]); |
|
1515 $lastKey=$key; |
|
1516 } |
|
1517 } |
|
1518 elsif ($algorithm==4) # KeyedTable16OfIndexedTables16 |
|
1519 { |
|
1520 die("Error: \"KeyedTable16OfIndexedTables16\" is only supported if generating source code\n"); |
|
1521 } |
|
1522 else |
|
1523 { |
|
1524 die("Error: internal error 15\n"); |
|
1525 } |
|
1526 } |
|
1527 my @characterCodes=sort({$a<=>$b} keys(%$characterCodes)); |
|
1528 if (@characterCodes>0) |
|
1529 { |
|
1530 die('The following '.($outputIsUnicode? 'foreign': 'Unicode').'characters have no conversion algorithm specified: ['.join(', ', map({sprintf('0x%x', $_)} @characterCodes))."\]\n"); |
|
1531 } |
|
1532 } |
|
1533 |