Commit | Line | Data |
---|---|---|
a0ed51b3 LW |
1 | #!../../miniperl |
2 | ||
7c6f5cd2 GS |
3 | use bytes; |
4 | ||
190eec7c | 5 | $UnicodeData = "Unicode.txt"; |
7c6f5cd2 | 6 | $SyllableData = "syllables.txt"; |
8836d2a5 | 7 | $PropData = "PropList.txt"; |
7c6f5cd2 | 8 | |
11695a73 | 9 | |
a0ed51b3 LW |
10 | # Note: we try to keep filenames unique within first 8 chars. Using |
11 | # subdirectories for the following helps. | |
289d4f09 ML |
12 | mkdir "In", 0755; |
13 | mkdir "Is", 0755; | |
14 | mkdir "To", 0755; | |
a0ed51b3 LW |
15 | |
16 | @todo = ( | |
17 | # typical | |
18 | ||
f59877d4 JH |
19 | # 005F: SPACING UNDERSCROE |
20 | ['IsWord', '$cat =~ /^[LMN]/ or $code eq "005F"', ''], | |
21 | ['IsAlnum', '$cat =~ /^[LMN]/', ''], | |
22 | ['IsAlpha', '$cat =~ /^[LM]/', ''], | |
23 | # 0009: HORIZONTAL TABULATION | |
24 | # 000A: LINE FEED | |
25 | # 000B: VERTICAL TABULATION | |
26 | # 000C: FORM FEED | |
27 | # 000D: CARRIAGE RETURN | |
3bec3564 | 28 | # 0020: SPACE |
f59877d4 JH |
29 | ['IsSpace', '$cat =~ /^Z/ || |
30 | $code =~ /^(0009|000A|000B|000C|000D)$/', ''], | |
3bec3564 JH |
31 | ['IsSpacePerl', |
32 | '$cat =~ /^Z/ || | |
33 | $code =~ /^(0009|000A|000C|000D)$/', ''], | |
f5868911 JH |
34 | ['IsBlank', '$code =~ /^(0020|0009)$/ || |
35 | $cat =~ /^Z[^lp]$/', ''], | |
b8c5462f | 36 | ['IsDigit', '$cat =~ /^Nd$/', ''], |
7c6f5cd2 | 37 | ['IsUpper', '$cat =~ /^L[ut]$/', ''], |
b8c5462f | 38 | ['IsLower', '$cat =~ /^Ll$/', ''], |
f59877d4 | 39 | ['IsASCII', '$code le "007f"', ''], |
b8c5462f | 40 | ['IsCntrl', '$cat =~ /^C/', ''], |
f59877d4 JH |
41 | ['IsGraph', '$cat =~ /^([LMNPS]|Co)/', ''], |
42 | ['IsPrint', '$cat =~ /^([LMNPS]|Co|Zs)/', ''], | |
43 | ['IsPunct', '$cat =~ /^P/', ''], | |
44 | # 003[0-9]: DIGIT ZERO..NINE, 00[46][1-6]: A..F, a..f | |
b8c5462f JH |
45 | ['IsXDigit', '$code =~ /^00(3[0-9]|[46][1-6])$/', ''], |
46 | ['ToUpper', '$up', '$up'], | |
47 | ['ToLower', '$down', '$down'], | |
48 | ['ToTitle', '$title', '$title'], | |
49 | ['ToDigit', '$dec ne ""', '$dec'], | |
a0ed51b3 LW |
50 | |
51 | # Name | |
52 | ||
53 | ['Name', '$name', '$name'], | |
54 | ||
55 | # Category | |
56 | ||
57 | ['Category', '$cat', '$cat'], | |
58 | ||
59 | # Normative | |
60 | ||
61 | ['IsM', '$cat =~ /^M/', ''], # Mark | |
62 | ['IsMn', '$cat eq "Mn"', ''], # Mark, Non-Spacing | |
63 | ['IsMc', '$cat eq "Mc"', ''], # Mark, Combining | |
7c6f5cd2 | 64 | ['IsMe', '$cat eq "Me"', ''], # Mark, Enclosing |
a0ed51b3 LW |
65 | |
66 | ['IsN', '$cat =~ /^N/', ''], # Number | |
67 | ['IsNd', '$cat eq "Nd"', ''], # Number, Decimal Digit | |
68 | ['IsNo', '$cat eq "No"', ''], # Number, Other | |
7c6f5cd2 | 69 | ['IsNl', '$cat eq "Nl"', ''], # Number, Letter |
a0ed51b3 | 70 | |
7c6f5cd2 | 71 | ['IsZ', '$cat =~ /^Z/', ''], # Separator |
a0ed51b3 LW |
72 | ['IsZs', '$cat eq "Zs"', ''], # Separator, Space |
73 | ['IsZl', '$cat eq "Zl"', ''], # Separator, Line | |
74 | ['IsZp', '$cat eq "Zp"', ''], # Separator, Paragraph | |
75 | ||
76 | ['IsC', '$cat =~ /^C/', ''], # Crazy | |
77 | ['IsCc', '$cat eq "Cc"', ''], # Other, Control or Format | |
78 | ['IsCo', '$cat eq "Co"', ''], # Other, Private Use | |
79 | ['IsCn', '$cat eq "Cn"', ''], # Other, Not Assigned | |
7c6f5cd2 GS |
80 | ['IsCf', '$cat eq "Cf"', ''], # Other, Format |
81 | ['IsCs', '$cat eq "Cs"', ''], # Other, Surrogate | |
82 | ['IsCn', 'Unassigned Code Value',$PropData], # Other, Not Assigned | |
a0ed51b3 LW |
83 | |
84 | # Informative | |
85 | ||
86 | ['IsL', '$cat =~ /^L/', ''], # Letter | |
87 | ['IsLu', '$cat eq "Lu"', ''], # Letter, Uppercase | |
88 | ['IsLl', '$cat eq "Ll"', ''], # Letter, Lowercase | |
89 | ['IsLt', '$cat eq "Lt"', ''], # Letter, Titlecase | |
90 | ['IsLm', '$cat eq "Lm"', ''], # Letter, Modifier | |
91 | ['IsLo', '$cat eq "Lo"', ''], # Letter, Other | |
92 | ||
93 | ['IsP', '$cat =~ /^P/', ''], # Punctuation | |
94 | ['IsPd', '$cat eq "Pd"', ''], # Punctuation, Dash | |
95 | ['IsPs', '$cat eq "Ps"', ''], # Punctuation, Open | |
96 | ['IsPe', '$cat eq "Pe"', ''], # Punctuation, Close | |
97 | ['IsPo', '$cat eq "Po"', ''], # Punctuation, Other | |
7c6f5cd2 GS |
98 | ['IsPc', '$cat eq "Pc"', ''], # Punctuation, Connector |
99 | ['IsPi', '$cat eq "Pi"', ''], # Punctuation, Initial quote | |
100 | ['IsPf', '$cat eq "Pf"', ''], # Punctuation, Final quote | |
a0ed51b3 LW |
101 | |
102 | ['IsS', '$cat =~ /^S/', ''], # Symbol | |
103 | ['IsSm', '$cat eq "Sm"', ''], # Symbol, Math | |
7c6f5cd2 | 104 | ['IsSk', '$cat eq "Sk"', ''], # Symbol, Modifier |
a0ed51b3 LW |
105 | ['IsSc', '$cat eq "Sc"', ''], # Symbol, Currency |
106 | ['IsSo', '$cat eq "So"', ''], # Symbol, Other | |
107 | ||
108 | # Combining class | |
109 | ['CombiningClass', '$comb', '$comb'], | |
110 | ||
111 | # BIDIRECTIONAL PROPERTIES | |
112 | ||
113 | ['Bidirectional', '$bid', '$bid'], | |
114 | ||
115 | # Strong types: | |
116 | ||
117 | ['IsBidiL', '$bid eq "L"', ''], # Left-Right; Most alphabetic, | |
118 | # syllabic, and logographic | |
119 | # characters (e.g., CJK | |
120 | # ideographs) | |
121 | ['IsBidiR', '$bid eq "R"', ''], # Right-Left; Arabic, Hebrew, | |
122 | # and punctuation specific to | |
123 | # those scripts | |
124 | ||
7c6f5cd2 GS |
125 | ['IsBidiLRE', '$bid eq "LRE"', ''], # Left-to-Right Embedding |
126 | ['IsBidiLRO', '$bid eq "LRO"', ''], # Left-to-Right Override | |
127 | ['IsBidiAL', '$bid eq "AL"', ''], # Right-to-Left Arabic | |
128 | ['IsBidiRLE', '$bid eq "RLE"', ''], # Right-to-Left Embedding | |
129 | ['IsBidiRLO', '$bid eq "RLO"', ''], # Right-to-Left Override | |
130 | ['IsBidiPDF', '$bid eq "PDF"', ''], # Pop Directional Format | |
131 | ['IsBidiNSM', '$bid eq "NSM"', ''], # Non-Spacing Mark | |
132 | ['IsBidiBN', '$bid eq "BN"', ''], # Boundary Neutral | |
133 | ||
a0ed51b3 LW |
134 | # Weak types: |
135 | ||
136 | ['IsBidiEN','$bid eq "EN"', ''], # European Number | |
137 | ['IsBidiES','$bid eq "ES"', ''], # European Number Separator | |
138 | ['IsBidiET','$bid eq "ET"', ''], # European Number Terminator | |
139 | ['IsBidiAN','$bid eq "AN"', ''], # Arabic Number | |
140 | ['IsBidiCS','$bid eq "CS"', ''], # Common Number Separator | |
141 | ||
142 | # Separators: | |
143 | ||
144 | ['IsBidiB', '$bid eq "B"', ''], # Block Separator | |
145 | ['IsBidiS', '$bid eq "S"', ''], # Segment Separator | |
146 | ||
147 | # Neutrals: | |
148 | ||
149 | ['IsBidiWS','$bid eq "WS"', ''], # Whitespace | |
150 | ['IsBidiON','$bid eq "ON"', ''], # Other Neutrals ; All other | |
151 | # characters: punctuation, | |
152 | # symbols | |
153 | ||
154 | # Decomposition | |
155 | ||
156 | ['Decomposition', '$decomp', '$decomp'], | |
157 | ['IsDecoCanon', '$decomp && $decomp !~ /^</', ''], | |
158 | ['IsDecoCompat', '$decomp =~ /^</', ''], | |
159 | ['IsDCfont', '$decomp =~ /^<font>/', ''], | |
160 | ['IsDCnoBreak', '$decomp =~ /^<noBreak>/', ''], | |
161 | ['IsDCinitial', '$decomp =~ /^<initial>/', ''], | |
f59877d4 | 162 | ['IsDCmedial', '$decomp =~ /^<medial>/', ''], |
a0ed51b3 LW |
163 | ['IsDCfinal', '$decomp =~ /^<final>/', ''], |
164 | ['IsDCisolated', '$decomp =~ /^<isolated>/', ''], | |
165 | ['IsDCcircle', '$decomp =~ /^<circle>/', ''], | |
166 | ['IsDCsuper', '$decomp =~ /^<super>/', ''], | |
167 | ['IsDCsub', '$decomp =~ /^<sub>/', ''], | |
168 | ['IsDCvertical', '$decomp =~ /^<vertical>/', ''], | |
169 | ['IsDCwide', '$decomp =~ /^<wide>/', ''], | |
170 | ['IsDCnarrow', '$decomp =~ /^<narrow>/', ''], | |
171 | ['IsDCsmall', '$decomp =~ /^<small>/', ''], | |
172 | ['IsDCsquare', '$decomp =~ /^<square>/', ''], | |
7c6f5cd2 | 173 | ['IsDCfraction', '$decomp =~ /^<fraction>/', ''], |
a0ed51b3 LW |
174 | ['IsDCcompat', '$decomp =~ /^<compat>/', ''], |
175 | ||
176 | # Number | |
177 | ||
e1b504a6 | 178 | ['Number', '$num ne ""', '$num'], |
a0ed51b3 LW |
179 | |
180 | # Mirrored | |
181 | ||
182 | ['IsMirrored', '$mir eq "Y"', ''], | |
183 | ||
184 | # Arabic | |
185 | ||
186 | ['ArabLink', '1', '$link'], | |
187 | ['ArabLnkGrp', '1', '$linkgroup'], | |
188 | ||
189 | # Jamo | |
190 | ||
191 | ['JamoShort', '1', '$short'], | |
499bfa7a JH |
192 | |
193 | # Syllables | |
194 | ||
7c6f5cd2 GS |
195 | syllable_defs(), |
196 | ||
a77b4ae5 GS |
197 | # Line break properties - Normative |
198 | ||
199 | ['IsLbrkBK','$brk eq "BK"', ''], # Mandatory Break | |
200 | ['IsLbrkCR','$brk eq "CR"', ''], # Carriage Return | |
201 | ['IsLbrkLF','$brk eq "LF"', ''], # Line Feed | |
202 | ['IsLbrkCM','$brk eq "CM"', ''], # Attached Characters and Combining Marks | |
203 | ['IsLbrkSG','$brk eq "SG"', ''], # Surrogates | |
204 | ['IsLbrkGL','$brk eq "GL"', ''], # Non-breaking (Glue) | |
205 | ['IsLbrkCB','$brk eq "CB"', ''], # Contingent Break Opportunity | |
206 | ['IsLbrkSP','$brk eq "SP"', ''], # Space | |
207 | ['IsLbrkZW','$brk eq "ZW"', ''], # Zero Width Space | |
208 | ||
209 | # Line break properties - Informative | |
210 | ['IsLbrkXX','$brk eq "XX"', ''], # Unknown | |
211 | ['IsLbrkOP','$brk eq "OP"', ''], # Opening Punctuation | |
212 | ['IsLbrkCL','$brk eq "CL"', ''], # Closing Punctuation | |
213 | ['IsLbrkQU','$brk eq "QU"', ''], # Ambiguous Quotation | |
214 | ['IsLbrkNS','$brk eq "NS"', ''], # Non Starter | |
215 | ['IsLbrkEX','$brk eq "EX"', ''], # Exclamation/Interrogation | |
216 | ['IsLbrkSY','$brk eq "SY"', ''], # Symbols Allowing Breaks | |
217 | ['IsLbrkIS','$brk eq "IS"', ''], # Infix Separator (Numeric) | |
218 | ['IsLbrkPR','$brk eq "PR"', ''], # Prefix (Numeric) | |
219 | ['IsLbrkPO','$brk eq "PO"', ''], # Postfix (Numeric) | |
220 | ['IsLbrkNU','$brk eq "NU"', ''], # Numeric | |
221 | ['IsLbrkAL','$brk eq "AL"', ''], # Ordinary Alphabetic and Symbol Characters | |
222 | ['IsLbrkID','$brk eq "ID"', ''], # Ideographic | |
223 | ['IsLbrkIN','$brk eq "IN"', ''], # Inseparable | |
224 | ['IsLbrkHY','$brk eq "HY"', ''], # Hyphen | |
225 | ['IsLbrkBB','$brk eq "BB"', ''], # Break Opportunity Before | |
226 | ['IsLbrkBA','$brk eq "BA"', ''], # Break Opportunity After | |
227 | ['IsLbrkSA','$brk eq "SA"', ''], # Complex Context (South East Asian) | |
228 | ['IsLbrkAI','$brk eq "AI"', ''], # Ambiguous (Alphabetic or Ideographic) | |
229 | ['IsLbrkB2','$brk eq "B2"', ''], # Break Opportunity Before and After | |
a0ed51b3 LW |
230 | ); |
231 | ||
232 | # This is not written for speed... | |
233 | ||
9fdf68be JH |
234 | my %InId; |
235 | my $InId = 0; | |
236 | ||
a0ed51b3 LW |
237 | foreach $file (@todo) { |
238 | my ($table, $wanted, $val) = @$file; | |
239 | next if @ARGV and not grep { $_ eq $table } @ARGV; | |
9fdf68be JH |
240 | print $table, "\n"; |
241 | $table =~ s/\W+//g; | |
2796c109 | 242 | if ($table =~ /^(Is|To)(.+)/) { |
a0ed51b3 LW |
243 | open(OUT, ">$1/$2.pl") or die "Can't create $1/$2.pl: $!\n"; |
244 | } | |
245 | else { | |
246 | open(OUT, ">$table.pl") or die "Can't create $table.pl: $!\n"; | |
247 | } | |
14055466 JH |
248 | print OUT <<EOH; |
249 | # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! | |
250 | # This file is built by $0 from e.g. $UnicodeData. | |
251 | # Any changes made here will be lost! | |
252 | EOH | |
a0ed51b3 LW |
253 | print OUT <<"END"; |
254 | return <<'END'; | |
255 | END | |
256 | print OUT proplist($table, $wanted, $val); | |
257 | print OUT "END\n"; | |
258 | close OUT; | |
259 | } | |
260 | ||
2796c109 JH |
261 | # Do Scripts before Blocks so that in case of naming conflicts |
262 | # the more natural one (Script) wins over the artificial one (Block). | |
263 | ||
264 | print "Scripts\n"; | |
265 | open(UD, 'Scripts.txt') or die "Can't open Scripts.txt: $!\n"; | |
266 | open(OUT, ">Scripts.pl") or die "Can't create Scripts.pl: $!\n"; | |
267 | print OUT <<EOH; | |
268 | # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! | |
269 | # This file is built by $0 from e.g. $UnicodeData. | |
270 | # Any changes made here will be lost! | |
271 | EOH | |
272 | print OUT <<"END"; | |
273 | return <<'END'; | |
274 | END | |
275 | ||
276 | my %Scripts; | |
277 | ||
278 | while (<UD>) { | |
279 | next if /^#/; | |
280 | next if /^$/; | |
281 | chomp; | |
282 | ($code, $last, $name) = /^([0-9a-f]+)\.\.([0-9a-f]+)\s+;\s+(.+)\s+\#/i; | |
283 | if ($name) { | |
284 | my $InName = lc($name); | |
285 | $InName =~ s/\b(\w)/uc($1)/ge; | |
286 | $InName =~ s/\W+//g; | |
287 | my $id; | |
288 | unless (exists $InId{$InName}) { | |
289 | print "\t$InName\n"; | |
290 | $id = $Scripts{$InName} = $InId{$InName} = $InId++; | |
291 | open(SCRIPT, ">In/$id.pl") or die "create In/$id.pl: $!\n"; | |
292 | print SCRIPT <<EOH; | |
293 | # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! | |
294 | # This file is built by $0 from e.g. $UnicodeData. | |
295 | # Any changes made here will be lost! | |
296 | return <<'END'; | |
297 | EOH | |
298 | close(SCRIPT); | |
299 | } else { | |
300 | $id = $InId{$InName}; | |
301 | } | |
302 | print OUT "$code\t$last\t$name\t# $InName In/$id.pl\n"; | |
303 | open(SCRIPT, ">>In/$id.pl"); | |
304 | print SCRIPT <<END; | |
305 | $code $last | |
306 | END | |
307 | close SCRIPT; | |
308 | } | |
309 | } | |
310 | ||
311 | for my $id (values %InId) { | |
312 | open(SCRIPT, ">>In/$id.pl"); | |
313 | print SCRIPT <<END2; | |
314 | END | |
315 | END2 | |
316 | close(SCRIPT); | |
317 | } | |
318 | ||
319 | print OUT "END\n"; | |
320 | close OUT; | |
321 | ||
a0ed51b3 LW |
322 | # Must treat blocks specially. |
323 | ||
324 | exit if @ARGV and not grep { $_ eq Block } @ARGV; | |
9fdf68be | 325 | print "Blocks\n"; |
7c6f5cd2 | 326 | open(UD, 'Blocks.txt') or die "Can't open Blocks.txt: $!\n"; |
9fdf68be | 327 | open(OUT, ">Blocks.pl") or die "Can't create Blocks.pl: $!\n"; |
14055466 JH |
328 | print OUT <<EOH; |
329 | # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! | |
330 | # This file is built by $0 from e.g. $UnicodeData. | |
331 | # Any changes made here will be lost! | |
332 | EOH | |
a0ed51b3 LW |
333 | print OUT <<"END"; |
334 | return <<'END'; | |
335 | END | |
336 | ||
337 | while (<UD>) { | |
338 | next if /^#/; | |
339 | next if /^$/; | |
340 | chomp; | |
9fdf68be | 341 | ($code, $last, $name) = /^([0-9a-f]+)\.\.([0-9a-f]+); (.+)/i; |
a0ed51b3 | 342 | if ($name) { |
2796c109 JH |
343 | my $InName = $name; |
344 | $InName =~ s/\W+//g; | |
345 | print "\t$InName\n"; | |
9fdf68be | 346 | my $id; |
2796c109 JH |
347 | # TODO: only the first one of Private Use blocks qualifies |
348 | unless (exists $InId{$InName}) { | |
349 | $InId{$InName} = $InId++; | |
350 | } elsif (exists $Scripts{$InName}) { | |
351 | $InName .= 'Block'; | |
352 | $InId{$InName} = $InId++; | |
9fdf68be | 353 | } |
2796c109 JH |
354 | $id = $InId{$InName}; |
355 | open(BLOCK, ">In/$id.pl") or die "create In/$id.pl: $!\n"; | |
356 | print OUT "$code\t$last\t$name\t# $InName In/$id.pl\n"; | |
14055466 JH |
357 | print BLOCK <<EOH; |
358 | # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! | |
359 | # This file is built by $0 from e.g. $UnicodeData. | |
360 | # Any changes made here will be lost! | |
361 | EOH | |
a0ed51b3 LW |
362 | print BLOCK <<"END2"; |
363 | return <<'END'; | |
364 | $code $last | |
365 | END | |
366 | END2 | |
367 | close BLOCK; | |
368 | } | |
369 | } | |
370 | ||
371 | print OUT "END\n"; | |
372 | close OUT; | |
373 | ||
9fdf68be JH |
374 | open(INID, ">In.pl"); |
375 | ||
376 | print INID <<EOH; | |
377 | # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! | |
378 | # This file is built by $0 from e.g. $UnicodeData. | |
379 | # Any changes made here will be lost! | |
380 | %utf8::In = ( | |
381 | EOH | |
382 | ||
383 | # Order doesn't matter but let's prettyprint anyway. | |
56ca2fc0 | 384 | foreach my $in (sort { $InId{$a} <=> $InId{$b} } keys %InId) { |
f178ed66 | 385 | printf INID "%-40s => %3d,\n", "'$in'", $InId{$in}; |
9fdf68be JH |
386 | } |
387 | ||
388 | print INID ");\n"; | |
389 | ||
390 | close(INID); | |
391 | ||
a0ed51b3 LW |
392 | ################################################## |
393 | ||
394 | sub proplist { | |
395 | my ($table, $wanted, $val) = @_; | |
396 | my @wanted; | |
397 | my $out; | |
398 | my $split; | |
399 | ||
7c6f5cd2 GS |
400 | return listFromPropFile($wanted) if $val eq $PropData; |
401 | ||
a0ed51b3 | 402 | if ($table =~ /^Arab/) { |
d357d9fe | 403 | open(UD, "ArabShap.txt") or warn "Can't open $table: $!"; |
a0ed51b3 LW |
404 | |
405 | $split = '($code, $name, $link, $linkgroup) = split(/; */);'; | |
406 | } | |
407 | elsif ($table =~ /^Jamo/) { | |
505afebf | 408 | open(UD, "Jamo.txt") or warn "Can't open $table: $!"; |
a0ed51b3 LW |
409 | |
410 | $split = '($code, $short, $name) = split(/; */); $code =~ s/^U\+//;'; | |
411 | } | |
499bfa7a | 412 | elsif ($table =~ /^IsSyl/) { |
7c6f5cd2 | 413 | open(UD, $SyllableData) or warn "Can't open $table: $!"; |
499bfa7a JH |
414 | |
415 | $split = '($code, $short, $syl) = split(/; */); $code =~ s/^U\+//;'; | |
416 | } | |
a77b4ae5 GS |
417 | elsif ($table =~ /^IsLbrk/) { |
418 | open(UD, "LineBrk.txt") or warn "Can't open $table: $!"; | |
419 | ||
50fc4248 | 420 | $split = '($code, $brk, $name) = /^([0-9a-f]+);(\w+) # (.+)/i;'; |
a77b4ae5 | 421 | } |
a0ed51b3 | 422 | else { |
11695a73 | 423 | open(UD, $UnicodeData) or warn "Can't open $UnicodeData: $!"; |
a0ed51b3 LW |
424 | |
425 | $split = '($code, $name, $cat, $comb, $bid, $decomp, $dec, $dig, $num, $mir, $uni1, | |
426 | $comment, $up, $down, $title) = split(/;/);'; | |
427 | } | |
428 | ||
429 | if ($table =~ /^(?:To|Is)[A-Z]/) { | |
430 | eval <<"END"; | |
431 | while (<UD>) { | |
432 | next if /^#/; | |
7c6f5cd2 GS |
433 | next if /^\\s/; |
434 | s/\\s+\$//; | |
a0ed51b3 LW |
435 | $split |
436 | if ($wanted) { | |
437 | push(\@wanted, [hex \$code, hex $val, \$name =~ /, First>\$/]); | |
438 | } | |
439 | } | |
440 | END | |
441 | die $@ if $@; | |
442 | ||
443 | while (@wanted) { | |
444 | $beg = shift @wanted; | |
445 | $last = $beg; | |
446 | while (@wanted and $wanted[0]->[0] == $last->[0] + 1 and | |
447 | (not $val or $wanted[0]->[1] == $last->[1] + 1)) { | |
448 | $last = shift @wanted; | |
449 | } | |
450 | $out .= sprintf "%04x", $beg->[0]; | |
451 | if ($beg->[2]) { | |
452 | $last = shift @wanted; | |
453 | } | |
454 | if ($beg == $last) { | |
455 | $out .= "\t"; | |
456 | } | |
457 | else { | |
458 | $out .= sprintf "\t%04x", $last->[0]; | |
459 | } | |
460 | $out .= sprintf "\t%04x", $beg->[1] if $val; | |
461 | $out .= "\n"; | |
462 | } | |
463 | } | |
464 | else { | |
465 | eval <<"END"; | |
466 | while (<UD>) { | |
467 | next if /^#/; | |
7c6f5cd2 | 468 | next if /^\\s*\$/; |
a0ed51b3 LW |
469 | chop; |
470 | $split | |
471 | if ($wanted) { | |
472 | push(\@wanted, [hex \$code, $val, \$name =~ /, First>\$/]); | |
473 | } | |
474 | } | |
475 | END | |
476 | die $@ if $@; | |
477 | ||
478 | while (@wanted) { | |
479 | $beg = shift @wanted; | |
480 | $last = $beg; | |
481 | while (@wanted and $wanted[0]->[0] == $last->[0] + 1 and | |
482 | ($wanted[0]->[1] eq $last->[1])) { | |
483 | $last = shift @wanted; | |
484 | } | |
485 | $out .= sprintf "%04x", $beg->[0]; | |
486 | if ($beg->[2]) { | |
487 | $last = shift @wanted; | |
488 | } | |
489 | if ($beg == $last) { | |
490 | $out .= "\t"; | |
491 | } | |
492 | else { | |
493 | $out .= sprintf "\t%04x", $last->[0]; | |
494 | } | |
495 | $out .= sprintf "\t%s\n", $beg->[1]; | |
496 | } | |
497 | } | |
498 | $out; | |
499 | } | |
11695a73 | 500 | |
7c6f5cd2 GS |
501 | sub listFromPropFile { |
502 | my ($wanted) = @_; | |
503 | my $out; | |
504 | ||
505 | open (UD, $PropData) or die "Can't open $PropData: $!\n"; | |
506 | local($/) = "\n" . '*' x 43 . "\n\nProperty dump for:"; # not 42? | |
507 | ||
508 | <UD>; | |
509 | while (<UD>) { | |
510 | chomp; | |
511 | if (s/0x[\d\w]+\s+\((.*?)\)// and $wanted eq $1) { | |
512 | s/\(\d+ chars\)//g; | |
513 | s/^\s+//mg; | |
514 | s/\s+$//mg; | |
515 | s/\.\./\t/g; | |
516 | $out = lc $_; | |
517 | last; | |
518 | } | |
519 | } | |
520 | close (UD); | |
521 | "$out\n"; | |
522 | } | |
523 | ||
524 | sub syllable_defs { | |
525 | my @defs; | |
526 | my %seen; | |
527 | ||
528 | open (SD, $SyllableData) or die "Can't open $SyllableData: $!\n"; | |
529 | while (<SD>) { | |
530 | next if /^\s*(#|$)/; | |
531 | s/\s+$//; | |
532 | ($code, $name, $syl) = split /; */; | |
533 | next unless $syl; | |
534 | push (@defs, ["IsSyl$syl", qq{\$syl eq "$syl"}, '']) | |
535 | unless $seen{$syl}++; | |
536 | } | |
537 | close (SD); | |
538 | return (@defs); | |
539 | } | |
540 | ||
6dd159d1 | 541 | # eof |