hytos / DTI_PID / DTI_PID / Tesseract-OCR / unicharambigs.5.html @ af64ec0d
이력 | 보기 | 이력해설 | 다운로드 (19.9 KB)
| 1 |
<!DOCTYPE html>
|
|---|---|
| 2 |
<html lang="en"> |
| 3 |
<head>
|
| 4 |
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"> |
| 5 |
<meta name="generator" content="AsciiDoc 8.6.10"> |
| 6 |
<title>UNICHARAMBIGS(5)</title> |
| 7 |
<style type="text/css"> |
| 8 |
/* Shared CSS for AsciiDoc xhtml11 and html5 backends */
|
| 9 |
|
| 10 |
/* Default font. */
|
| 11 |
body {
|
| 12 |
font-family: Georgia,serif;
|
| 13 |
}
|
| 14 |
|
| 15 |
/* Title font. */
|
| 16 |
h1, h2, h3, h4, h5, h6,
|
| 17 |
div.title, caption.title,
|
| 18 |
thead, p.table.header,
|
| 19 |
#toctitle,
|
| 20 |
#author, #revnumber, #revdate, #revremark,
|
| 21 |
#footer {
|
| 22 |
font-family: Arial,Helvetica,sans-serif;
|
| 23 |
}
|
| 24 |
|
| 25 |
body {
|
| 26 |
margin: 1em 5% 1em 5%;
|
| 27 |
}
|
| 28 |
|
| 29 |
a {
|
| 30 |
color: blue;
|
| 31 |
text-decoration: underline;
|
| 32 |
}
|
| 33 |
a:visited {
|
| 34 |
color: fuchsia;
|
| 35 |
}
|
| 36 |
|
| 37 |
em {
|
| 38 |
font-style: italic;
|
| 39 |
color: navy;
|
| 40 |
}
|
| 41 |
|
| 42 |
strong {
|
| 43 |
font-weight: bold;
|
| 44 |
color: #083194;
|
| 45 |
}
|
| 46 |
|
| 47 |
h1, h2, h3, h4, h5, h6 {
|
| 48 |
color: #527bbd;
|
| 49 |
margin-top: 1.2em;
|
| 50 |
margin-bottom: 0.5em;
|
| 51 |
line-height: 1.3;
|
| 52 |
}
|
| 53 |
|
| 54 |
h1, h2, h3 {
|
| 55 |
border-bottom: 2px solid silver;
|
| 56 |
}
|
| 57 |
h2 {
|
| 58 |
padding-top: 0.5em;
|
| 59 |
}
|
| 60 |
h3 {
|
| 61 |
float: left;
|
| 62 |
}
|
| 63 |
h3 + * {
|
| 64 |
clear: left;
|
| 65 |
}
|
| 66 |
h5 {
|
| 67 |
font-size: 1.0em;
|
| 68 |
}
|
| 69 |
|
| 70 |
div.sectionbody {
|
| 71 |
margin-left: 0;
|
| 72 |
}
|
| 73 |
|
| 74 |
hr {
|
| 75 |
border: 1px solid silver;
|
| 76 |
}
|
| 77 |
|
| 78 |
p {
|
| 79 |
margin-top: 0.5em;
|
| 80 |
margin-bottom: 0.5em;
|
| 81 |
}
|
| 82 |
|
| 83 |
ul, ol, li > p {
|
| 84 |
margin-top: 0;
|
| 85 |
}
|
| 86 |
ul > li { color: #aaa; }
|
| 87 |
ul > li > * { color: black; }
|
| 88 |
|
| 89 |
.monospaced, code, pre {
|
| 90 |
font-family: "Courier New", Courier, monospace;
|
| 91 |
font-size: inherit;
|
| 92 |
color: navy;
|
| 93 |
padding: 0;
|
| 94 |
margin: 0;
|
| 95 |
}
|
| 96 |
pre {
|
| 97 |
white-space: pre-wrap;
|
| 98 |
}
|
| 99 |
|
| 100 |
#author {
|
| 101 |
color: #527bbd;
|
| 102 |
font-weight: bold;
|
| 103 |
font-size: 1.1em;
|
| 104 |
}
|
| 105 |
#email {
|
| 106 |
}
|
| 107 |
#revnumber, #revdate, #revremark {
|
| 108 |
}
|
| 109 |
|
| 110 |
#footer {
|
| 111 |
font-size: small;
|
| 112 |
border-top: 2px solid silver;
|
| 113 |
padding-top: 0.5em;
|
| 114 |
margin-top: 4.0em;
|
| 115 |
}
|
| 116 |
#footer-text {
|
| 117 |
float: left;
|
| 118 |
padding-bottom: 0.5em;
|
| 119 |
}
|
| 120 |
#footer-badges {
|
| 121 |
float: right;
|
| 122 |
padding-bottom: 0.5em;
|
| 123 |
}
|
| 124 |
|
| 125 |
#preamble {
|
| 126 |
margin-top: 1.5em;
|
| 127 |
margin-bottom: 1.5em;
|
| 128 |
}
|
| 129 |
div.imageblock, div.exampleblock, div.verseblock,
|
| 130 |
div.quoteblock, div.literalblock, div.listingblock, div.sidebarblock,
|
| 131 |
div.admonitionblock {
|
| 132 |
margin-top: 1.0em;
|
| 133 |
margin-bottom: 1.5em;
|
| 134 |
}
|
| 135 |
div.admonitionblock {
|
| 136 |
margin-top: 2.0em;
|
| 137 |
margin-bottom: 2.0em;
|
| 138 |
margin-right: 10%;
|
| 139 |
color: #606060;
|
| 140 |
}
|
| 141 |
|
| 142 |
div.content { /* Block element content. */
|
| 143 |
padding: 0;
|
| 144 |
}
|
| 145 |
|
| 146 |
/* Block element titles. */
|
| 147 |
div.title, caption.title {
|
| 148 |
color: #527bbd;
|
| 149 |
font-weight: bold;
|
| 150 |
text-align: left;
|
| 151 |
margin-top: 1.0em;
|
| 152 |
margin-bottom: 0.5em;
|
| 153 |
}
|
| 154 |
div.title + * {
|
| 155 |
margin-top: 0;
|
| 156 |
}
|
| 157 |
|
| 158 |
td div.title:first-child {
|
| 159 |
margin-top: 0.0em;
|
| 160 |
}
|
| 161 |
div.content div.title:first-child {
|
| 162 |
margin-top: 0.0em;
|
| 163 |
}
|
| 164 |
div.content + div.title {
|
| 165 |
margin-top: 0.0em;
|
| 166 |
}
|
| 167 |
|
| 168 |
div.sidebarblock > div.content {
|
| 169 |
background: #ffffee;
|
| 170 |
border: 1px solid #dddddd;
|
| 171 |
border-left: 4px solid #f0f0f0;
|
| 172 |
padding: 0.5em;
|
| 173 |
}
|
| 174 |
|
| 175 |
div.listingblock > div.content {
|
| 176 |
border: 1px solid #dddddd;
|
| 177 |
border-left: 5px solid #f0f0f0;
|
| 178 |
background: #f8f8f8;
|
| 179 |
padding: 0.5em;
|
| 180 |
}
|
| 181 |
|
| 182 |
div.quoteblock, div.verseblock {
|
| 183 |
padding-left: 1.0em;
|
| 184 |
margin-left: 1.0em;
|
| 185 |
margin-right: 10%;
|
| 186 |
border-left: 5px solid #f0f0f0;
|
| 187 |
color: #888;
|
| 188 |
}
|
| 189 |
|
| 190 |
div.quoteblock > div.attribution {
|
| 191 |
padding-top: 0.5em;
|
| 192 |
text-align: right;
|
| 193 |
}
|
| 194 |
|
| 195 |
div.verseblock > pre.content {
|
| 196 |
font-family: inherit;
|
| 197 |
font-size: inherit;
|
| 198 |
}
|
| 199 |
div.verseblock > div.attribution {
|
| 200 |
padding-top: 0.75em;
|
| 201 |
text-align: left;
|
| 202 |
}
|
| 203 |
/* DEPRECATED: Pre version 8.2.7 verse style literal block. */
|
| 204 |
div.verseblock + div.attribution {
|
| 205 |
text-align: left;
|
| 206 |
}
|
| 207 |
|
| 208 |
div.admonitionblock .icon {
|
| 209 |
vertical-align: top;
|
| 210 |
font-size: 1.1em;
|
| 211 |
font-weight: bold;
|
| 212 |
text-decoration: underline;
|
| 213 |
color: #527bbd;
|
| 214 |
padding-right: 0.5em;
|
| 215 |
}
|
| 216 |
div.admonitionblock td.content {
|
| 217 |
padding-left: 0.5em;
|
| 218 |
border-left: 3px solid #dddddd;
|
| 219 |
}
|
| 220 |
|
| 221 |
div.exampleblock > div.content {
|
| 222 |
border-left: 3px solid #dddddd;
|
| 223 |
padding-left: 0.5em;
|
| 224 |
}
|
| 225 |
|
| 226 |
div.imageblock div.content { padding-left: 0; }
|
| 227 |
span.image img { border-style: none; vertical-align: text-bottom; }
|
| 228 |
a.image:visited { color: white; }
|
| 229 |
|
| 230 |
dl {
|
| 231 |
margin-top: 0.8em;
|
| 232 |
margin-bottom: 0.8em;
|
| 233 |
}
|
| 234 |
dt {
|
| 235 |
margin-top: 0.5em;
|
| 236 |
margin-bottom: 0;
|
| 237 |
font-style: normal;
|
| 238 |
color: navy;
|
| 239 |
}
|
| 240 |
dd > *:first-child {
|
| 241 |
margin-top: 0.1em;
|
| 242 |
}
|
| 243 |
|
| 244 |
ul, ol {
|
| 245 |
list-style-position: outside;
|
| 246 |
}
|
| 247 |
ol.arabic {
|
| 248 |
list-style-type: decimal;
|
| 249 |
}
|
| 250 |
ol.loweralpha {
|
| 251 |
list-style-type: lower-alpha;
|
| 252 |
}
|
| 253 |
ol.upperalpha {
|
| 254 |
list-style-type: upper-alpha;
|
| 255 |
}
|
| 256 |
ol.lowerroman {
|
| 257 |
list-style-type: lower-roman;
|
| 258 |
}
|
| 259 |
ol.upperroman {
|
| 260 |
list-style-type: upper-roman;
|
| 261 |
}
|
| 262 |
|
| 263 |
div.compact ul, div.compact ol,
|
| 264 |
div.compact p, div.compact p,
|
| 265 |
div.compact div, div.compact div {
|
| 266 |
margin-top: 0.1em;
|
| 267 |
margin-bottom: 0.1em;
|
| 268 |
}
|
| 269 |
|
| 270 |
tfoot {
|
| 271 |
font-weight: bold;
|
| 272 |
}
|
| 273 |
td > div.verse {
|
| 274 |
white-space: pre;
|
| 275 |
}
|
| 276 |
|
| 277 |
div.hdlist {
|
| 278 |
margin-top: 0.8em;
|
| 279 |
margin-bottom: 0.8em;
|
| 280 |
}
|
| 281 |
div.hdlist tr {
|
| 282 |
padding-bottom: 15px;
|
| 283 |
}
|
| 284 |
dt.hdlist1.strong, td.hdlist1.strong {
|
| 285 |
font-weight: bold;
|
| 286 |
}
|
| 287 |
td.hdlist1 {
|
| 288 |
vertical-align: top;
|
| 289 |
font-style: normal;
|
| 290 |
padding-right: 0.8em;
|
| 291 |
color: navy;
|
| 292 |
}
|
| 293 |
td.hdlist2 {
|
| 294 |
vertical-align: top;
|
| 295 |
}
|
| 296 |
div.hdlist.compact tr {
|
| 297 |
margin: 0;
|
| 298 |
padding-bottom: 0;
|
| 299 |
}
|
| 300 |
|
| 301 |
.comment {
|
| 302 |
background: yellow;
|
| 303 |
}
|
| 304 |
|
| 305 |
.footnote, .footnoteref {
|
| 306 |
font-size: 0.8em;
|
| 307 |
}
|
| 308 |
|
| 309 |
span.footnote, span.footnoteref {
|
| 310 |
vertical-align: super;
|
| 311 |
}
|
| 312 |
|
| 313 |
#footnotes {
|
| 314 |
margin: 20px 0 20px 0;
|
| 315 |
padding: 7px 0 0 0;
|
| 316 |
}
|
| 317 |
|
| 318 |
#footnotes div.footnote {
|
| 319 |
margin: 0 0 5px 0;
|
| 320 |
}
|
| 321 |
|
| 322 |
#footnotes hr {
|
| 323 |
border: none;
|
| 324 |
border-top: 1px solid silver;
|
| 325 |
height: 1px;
|
| 326 |
text-align: left;
|
| 327 |
margin-left: 0;
|
| 328 |
width: 20%;
|
| 329 |
min-width: 100px;
|
| 330 |
}
|
| 331 |
|
| 332 |
div.colist td {
|
| 333 |
padding-right: 0.5em;
|
| 334 |
padding-bottom: 0.3em;
|
| 335 |
vertical-align: top;
|
| 336 |
}
|
| 337 |
div.colist td img {
|
| 338 |
margin-top: 0.3em;
|
| 339 |
}
|
| 340 |
|
| 341 |
@media print {
|
| 342 |
#footer-badges { display: none; }
|
| 343 |
}
|
| 344 |
|
| 345 |
#toc {
|
| 346 |
margin-bottom: 2.5em;
|
| 347 |
}
|
| 348 |
|
| 349 |
#toctitle {
|
| 350 |
color: #527bbd;
|
| 351 |
font-size: 1.1em;
|
| 352 |
font-weight: bold;
|
| 353 |
margin-top: 1.0em;
|
| 354 |
margin-bottom: 0.1em;
|
| 355 |
}
|
| 356 |
|
| 357 |
div.toclevel0, div.toclevel1, div.toclevel2, div.toclevel3, div.toclevel4 {
|
| 358 |
margin-top: 0;
|
| 359 |
margin-bottom: 0;
|
| 360 |
}
|
| 361 |
div.toclevel2 {
|
| 362 |
margin-left: 2em;
|
| 363 |
font-size: 0.9em;
|
| 364 |
}
|
| 365 |
div.toclevel3 {
|
| 366 |
margin-left: 4em;
|
| 367 |
font-size: 0.9em;
|
| 368 |
}
|
| 369 |
div.toclevel4 {
|
| 370 |
margin-left: 6em;
|
| 371 |
font-size: 0.9em;
|
| 372 |
}
|
| 373 |
|
| 374 |
span.aqua { color: aqua; }
|
| 375 |
span.black { color: black; }
|
| 376 |
span.blue { color: blue; }
|
| 377 |
span.fuchsia { color: fuchsia; }
|
| 378 |
span.gray { color: gray; }
|
| 379 |
span.green { color: green; }
|
| 380 |
span.lime { color: lime; }
|
| 381 |
span.maroon { color: maroon; }
|
| 382 |
span.navy { color: navy; }
|
| 383 |
span.olive { color: olive; }
|
| 384 |
span.purple { color: purple; }
|
| 385 |
span.red { color: red; }
|
| 386 |
span.silver { color: silver; }
|
| 387 |
span.teal { color: teal; }
|
| 388 |
span.white { color: white; }
|
| 389 |
span.yellow { color: yellow; }
|
| 390 |
|
| 391 |
span.aqua-background { background: aqua; }
|
| 392 |
span.black-background { background: black; }
|
| 393 |
span.blue-background { background: blue; }
|
| 394 |
span.fuchsia-background { background: fuchsia; }
|
| 395 |
span.gray-background { background: gray; }
|
| 396 |
span.green-background { background: green; }
|
| 397 |
span.lime-background { background: lime; }
|
| 398 |
span.maroon-background { background: maroon; }
|
| 399 |
span.navy-background { background: navy; }
|
| 400 |
span.olive-background { background: olive; }
|
| 401 |
span.purple-background { background: purple; }
|
| 402 |
span.red-background { background: red; }
|
| 403 |
span.silver-background { background: silver; }
|
| 404 |
span.teal-background { background: teal; }
|
| 405 |
span.white-background { background: white; }
|
| 406 |
span.yellow-background { background: yellow; }
|
| 407 |
|
| 408 |
span.big { font-size: 2em; }
|
| 409 |
span.small { font-size: 0.6em; }
|
| 410 |
|
| 411 |
span.underline { text-decoration: underline; }
|
| 412 |
span.overline { text-decoration: overline; }
|
| 413 |
span.line-through { text-decoration: line-through; }
|
| 414 |
|
| 415 |
div.unbreakable { page-break-inside: avoid; }
|
| 416 |
|
| 417 |
|
| 418 |
/*
|
| 419 |
* xhtml11 specific
|
| 420 |
*
|
| 421 |
* */
|
| 422 |
|
| 423 |
div.tableblock {
|
| 424 |
margin-top: 1.0em;
|
| 425 |
margin-bottom: 1.5em;
|
| 426 |
}
|
| 427 |
div.tableblock > table {
|
| 428 |
border: 3px solid #527bbd;
|
| 429 |
}
|
| 430 |
thead, p.table.header {
|
| 431 |
font-weight: bold;
|
| 432 |
color: #527bbd;
|
| 433 |
}
|
| 434 |
p.table {
|
| 435 |
margin-top: 0;
|
| 436 |
}
|
| 437 |
/* Because the table frame attribute is overriden by CSS in most browsers. */
|
| 438 |
div.tableblock > table[frame="void"] {
|
| 439 |
border-style: none;
|
| 440 |
}
|
| 441 |
div.tableblock > table[frame="hsides"] {
|
| 442 |
border-left-style: none;
|
| 443 |
border-right-style: none;
|
| 444 |
}
|
| 445 |
div.tableblock > table[frame="vsides"] {
|
| 446 |
border-top-style: none;
|
| 447 |
border-bottom-style: none;
|
| 448 |
}
|
| 449 |
|
| 450 |
|
| 451 |
/*
|
| 452 |
* html5 specific
|
| 453 |
*
|
| 454 |
* */
|
| 455 |
|
| 456 |
table.tableblock {
|
| 457 |
margin-top: 1.0em;
|
| 458 |
margin-bottom: 1.5em;
|
| 459 |
}
|
| 460 |
thead, p.tableblock.header {
|
| 461 |
font-weight: bold;
|
| 462 |
color: #527bbd;
|
| 463 |
}
|
| 464 |
p.tableblock {
|
| 465 |
margin-top: 0;
|
| 466 |
}
|
| 467 |
table.tableblock {
|
| 468 |
border-width: 3px;
|
| 469 |
border-spacing: 0px;
|
| 470 |
border-style: solid;
|
| 471 |
border-color: #527bbd;
|
| 472 |
border-collapse: collapse;
|
| 473 |
}
|
| 474 |
th.tableblock, td.tableblock {
|
| 475 |
border-width: 1px;
|
| 476 |
padding: 4px;
|
| 477 |
border-style: solid;
|
| 478 |
border-color: #527bbd;
|
| 479 |
}
|
| 480 |
|
| 481 |
table.tableblock.frame-topbot {
|
| 482 |
border-left-style: hidden;
|
| 483 |
border-right-style: hidden;
|
| 484 |
}
|
| 485 |
table.tableblock.frame-sides {
|
| 486 |
border-top-style: hidden;
|
| 487 |
border-bottom-style: hidden;
|
| 488 |
}
|
| 489 |
table.tableblock.frame-none {
|
| 490 |
border-style: hidden;
|
| 491 |
}
|
| 492 |
|
| 493 |
th.tableblock.halign-left, td.tableblock.halign-left {
|
| 494 |
text-align: left;
|
| 495 |
}
|
| 496 |
th.tableblock.halign-center, td.tableblock.halign-center {
|
| 497 |
text-align: center;
|
| 498 |
}
|
| 499 |
th.tableblock.halign-right, td.tableblock.halign-right {
|
| 500 |
text-align: right;
|
| 501 |
}
|
| 502 |
|
| 503 |
th.tableblock.valign-top, td.tableblock.valign-top {
|
| 504 |
vertical-align: top;
|
| 505 |
}
|
| 506 |
th.tableblock.valign-middle, td.tableblock.valign-middle {
|
| 507 |
vertical-align: middle;
|
| 508 |
}
|
| 509 |
th.tableblock.valign-bottom, td.tableblock.valign-bottom {
|
| 510 |
vertical-align: bottom;
|
| 511 |
}
|
| 512 |
|
| 513 |
|
| 514 |
/*
|
| 515 |
* manpage specific
|
| 516 |
*
|
| 517 |
* */
|
| 518 |
|
| 519 |
body.manpage h1 {
|
| 520 |
padding-top: 0.5em;
|
| 521 |
padding-bottom: 0.5em;
|
| 522 |
border-top: 2px solid silver;
|
| 523 |
border-bottom: 2px solid silver;
|
| 524 |
}
|
| 525 |
body.manpage h2 {
|
| 526 |
border-style: none;
|
| 527 |
}
|
| 528 |
body.manpage div.sectionbody {
|
| 529 |
margin-left: 3em;
|
| 530 |
}
|
| 531 |
|
| 532 |
@media print {
|
| 533 |
body.manpage div#toc { display: none; }
|
| 534 |
}
|
| 535 |
|
| 536 |
|
| 537 |
</style>
|
| 538 |
<script type="text/javascript"> |
| 539 |
/*<+'])');
|
| 582 |
// Function that scans the DOM tree for header elements (the DOM2
|
| 583 |
// nodeIterator API would be a better technique but not supported by all
|
| 584 |
// browsers).
|
| 585 |
var iterate = function (el) {
|
| 586 |
for (var i = el.firstChild; i != null; i = i.nextSibling) {
|
| 587 |
if (i.nodeType == 1 /* Node.ELEMENT_NODE */) {
|
| 588 |
var mo = re.exec(i.tagName);
|
| 589 |
if (mo && (i.getAttribute("class") || i.getAttribute("className")) != "float") {
|
| 590 |
result[result.length] = new TocEntry(i, getText(i), mo[1]-1);
|
| 591 |
}
|
| 592 |
iterate(i);
|
| 593 |
}
|
| 594 |
}
|
| 595 |
}
|
| 596 |
iterate(el);
|
| 597 |
return result;
|
| 598 |
}
|
| 599 |
|
| 600 |
var toc = document.getElementById("toc");
|
| 601 |
if (!toc) {
|
| 602 |
return;
|
| 603 |
}
|
| 604 |
|
| 605 |
// Delete existing TOC entries in case we're reloading the TOC.
|
| 606 |
var tocEntriesToRemove = [];
|
| 607 |
var i;
|
| 608 |
for (i = 0; i < toc.childNodes.length; i++) {
|
| 609 |
var entry = toc.childNodes[i];
|
| 610 |
if (entry.nodeName.toLowerCase() == 'div'
|
| 611 |
&& entry.getAttribute("class")
|
| 612 |
&& entry.getAttribute("class").match(/^toclevel/))
|
| 613 |
tocEntriesToRemove.push(entry);
|
| 614 |
}
|
| 615 |
for (i = 0; i < tocEntriesToRemove.length; i++) {
|
| 616 |
toc.removeChild(tocEntriesToRemove[i]);
|
| 617 |
}
|
| 618 |
|
| 619 |
// Rebuild TOC entries.
|
| 620 |
var entries = tocEntries(document.getElementById("content"), toclevels);
|
| 621 |
for (var i = 0; i < entries.length; ++i) {
|
| 622 |
var entry = entries[i];
|
| 623 |
if (entry.element.id == "")
|
| 624 |
entry.element.id = "_toc_" + i;
|
| 625 |
var a = document.createElement("a");
|
| 626 |
a.href = "#" + entry.element.id;
|
| 627 |
a.appendChild(document.createTextNode(entry.text));
|
| 628 |
var div = document.createElement("div");
|
| 629 |
div.appendChild(a);
|
| 630 |
div.className = "toclevel" + entry.toclevel;
|
| 631 |
toc.appendChild(div);
|
| 632 |
}
|
| 633 |
if (entries.length == 0)
|
| 634 |
toc.parentNode.removeChild(toc);
|
| 635 |
},
|
| 636 |
|
| 637 |
|
| 638 |
/////////////////////////////////////////////////////////////////////
|
| 639 |
// Footnotes generator
|
| 640 |
/////////////////////////////////////////////////////////////////////
|
| 641 |
|
| 642 |
/* Based on footnote generation code from:
|
| 643 |
* http://www.brandspankingnew.net/archive/2005/07/format_footnote.html
|
| 644 |
*/
|
| 645 |
|
| 646 |
footnotes: function () {
|
| 647 |
// Delete existing footnote entries in case we're reloading the footnodes.
|
| 648 |
var i;
|
| 649 |
var noteholder = document.getElementById("footnotes");
|
| 650 |
if (!noteholder) {
|
| 651 |
return;
|
| 652 |
}
|
| 653 |
var entriesToRemove = [];
|
| 654 |
for (i = 0; i < noteholder.childNodes.length; i++) {
|
| 655 |
var entry = noteholder.childNodes[i];
|
| 656 |
if (entry.nodeName.toLowerCase() == 'div' && entry.getAttribute("class") == "footnote")
|
| 657 |
entriesToRemove.push(entry);
|
| 658 |
}
|
| 659 |
for (i = 0; i < entriesToRemove.length; i++) {
|
| 660 |
noteholder.removeChild(entriesToRemove[i]);
|
| 661 |
}
|
| 662 |
|
| 663 |
// Rebuild footnote entries.
|
| 664 |
var cont = document.getElementById("content");
|
| 665 |
var spans = cont.getElementsByTagName("span");
|
| 666 |
var refs = {};
|
| 667 |
var n = 0;
|
| 668 |
for (i=0; i<spans.length; i++) {
|
| 669 |
if (spans[i].className == "footnote") {
|
| 670 |
n++;
|
| 671 |
var note = spans[i].getAttribute("data-note");
|
| 672 |
if (!note) {
|
| 673 |
// Use [\s\S] in place of . so multi-line matches work.
|
| 674 |
// Because JavaScript has no s (dotall) regex flag.
|
| 675 |
note = spans[i].innerHTML.match(/\s*\[([\s\S]*)]\s*/)[1];
|
| 676 |
spans[i].innerHTML =
|
| 677 |
"[<a id='_footnoteref_" + n + "' href='#_footnote_" + n +
|
| 678 |
"' title='View footnote' class='footnote'>" + n + "</a>]";
|
| 679 |
spans[i].setAttribute("data-note", note);
|
| 680 |
}
|
| 681 |
noteholder.innerHTML +=
|
| 682 |
"<div class='footnote' id='_footnote_" + n + "'>" +
|
| 683 |
"<a href='#_footnoteref_" + n + "' title='Return to text'>" +
|
| 684 |
n + "</a>. " + note + "</div>";
|
| 685 |
var id =spans[i].getAttribute("id");
|
| 686 |
if (id != null) refs["#"+id] = n;
|
| 687 |
}
|
| 688 |
}
|
| 689 |
if (n == 0)
|
| 690 |
noteholder.parentNode.removeChild(noteholder);
|
| 691 |
else {
|
| 692 |
// Process footnoterefs.
|
| 693 |
for (i=0; i<spans.length; i++) {
|
| 694 |
if (spans[i].className == "footnoteref") {
|
| 695 |
var href = spans[i].getElementsByTagName("a")[0].getAttribute("href");
|
| 696 |
href = href.match(/#.*/)[0]; // Because IE return full URL.
|
| 697 |
n = refs[href];
|
| 698 |
spans[i].innerHTML =
|
| 699 |
"[<a href='#_footnote_" + n +
|
| 700 |
"' title='View footnote' class='footnote'>" + n + "</a>]";
|
| 701 |
}
|
| 702 |
}
|
| 703 |
}
|
| 704 |
},
|
| 705 |
|
| 706 |
install: function(toclevels) {
|
| 707 |
var timerId;
|
| 708 |
|
| 709 |
function reinstall() {
|
| 710 |
asciidoc.footnotes();
|
| 711 |
if (toclevels) {
|
| 712 |
asciidoc.toc(toclevels);
|
| 713 |
}
|
| 714 |
}
|
| 715 |
|
| 716 |
function reinstallAndRemoveTimer() {
|
| 717 |
clearInterval(timerId);
|
| 718 |
reinstall();
|
| 719 |
}
|
| 720 |
|
| 721 |
timerId = setInterval(reinstall, 500);
|
| 722 |
if (document.addEventListener)
|
| 723 |
document.addEventListener("DOMContentLoaded", reinstallAndRemoveTimer, false);
|
| 724 |
else
|
| 725 |
window.onload = reinstallAndRemoveTimer;
|
| 726 |
}
|
| 727 |
|
| 728 |
}
|
| 729 |
asciidoc.install();
|
| 730 |
/*]]>*/
|
| 731 |
</script>
|
| 732 |
</head>
|
| 733 |
<body class="article"> |
| 734 |
<div id="header"> |
| 735 |
<h1>UNICHARAMBIGS(5)</h1> |
| 736 |
</div>
|
| 737 |
<div id="content"> |
| 738 |
<div class="sect1"> |
| 739 |
<h2 id="_name">NAME</h2> |
| 740 |
<div class="sectionbody"> |
| 741 |
<div class="paragraph"><p>unicharambigs - Tesseract unicharset ambiguities</p></div> |
| 742 |
</div>
|
| 743 |
</div>
|
| 744 |
<div class="sect1"> |
| 745 |
<h2 id="_description">DESCRIPTION</h2> |
| 746 |
<div class="sectionbody"> |
| 747 |
<div class="paragraph"><p>The unicharambigs file (a component of traineddata, see combine_tessdata(1) ) |
| 748 |
is used by Tesseract to represent possible ambiguities between characters, |
| 749 |
or groups of characters.</p></div> |
| 750 |
<div class="paragraph"><p>The file contains a number of lines, laid out as follow:</p></div> |
| 751 |
<div class="literalblock"> |
| 752 |
<div class="content monospaced"> |
| 753 |
<pre>[num] <TAB> [char(s)] <TAB> [num] <TAB> [char(s)] <TAB> [num]</pre> |
| 754 |
</div></div> |
| 755 |
<div class="hdlist"><table> |
| 756 |
<tr>
|
| 757 |
<td class="hdlist1"> |
| 758 |
Field one |
| 759 |
<br>
|
| 760 |
</td>
|
| 761 |
<td class="hdlist2"> |
| 762 |
<p style="margin-top: 0;"> |
| 763 |
the number of characters contained in field two |
| 764 |
</p>
|
| 765 |
</td>
|
| 766 |
</tr>
|
| 767 |
<tr>
|
| 768 |
<td class="hdlist1"> |
| 769 |
Field two |
| 770 |
<br>
|
| 771 |
</td>
|
| 772 |
<td class="hdlist2"> |
| 773 |
<p style="margin-top: 0;"> |
| 774 |
the character sequence to be replaced |
| 775 |
</p>
|
| 776 |
</td>
|
| 777 |
</tr>
|
| 778 |
<tr>
|
| 779 |
<td class="hdlist1"> |
| 780 |
Field three |
| 781 |
<br>
|
| 782 |
</td>
|
| 783 |
<td class="hdlist2"> |
| 784 |
<p style="margin-top: 0;"> |
| 785 |
the number of characters contained in field four |
| 786 |
</p>
|
| 787 |
</td>
|
| 788 |
</tr>
|
| 789 |
<tr>
|
| 790 |
<td class="hdlist1"> |
| 791 |
Field four |
| 792 |
<br>
|
| 793 |
</td>
|
| 794 |
<td class="hdlist2"> |
| 795 |
<p style="margin-top: 0;"> |
| 796 |
the character sequence used to replace field two |
| 797 |
</p>
|
| 798 |
</td>
|
| 799 |
</tr>
|
| 800 |
<tr>
|
| 801 |
<td class="hdlist1"> |
| 802 |
Field five |
| 803 |
<br>
|
| 804 |
</td>
|
| 805 |
<td class="hdlist2"> |
| 806 |
<p style="margin-top: 0;"> |
| 807 |
contains either 1 or 0. 1 denotes a mandatory |
| 808 |
replacement, 0 denotes an optional replacement. |
| 809 |
</p>
|
| 810 |
</td>
|
| 811 |
</tr>
|
| 812 |
</table></div> |
| 813 |
<div class="paragraph"><p>Characters appearing in fields two and four should appear in |
| 814 |
unicharset. The numbers in fields one and three refer to the |
| 815 |
number of unichars (not bytes).</p></div> |
| 816 |
</div>
|
| 817 |
</div>
|
| 818 |
<div class="sect1"> |
| 819 |
<h2 id="_example">EXAMPLE</h2> |
| 820 |
<div class="sectionbody"> |
| 821 |
<div class="literalblock"> |
| 822 |
<div class="content monospaced"> |
| 823 |
<pre>v1
|
| 824 |
2 ' ' 1 " 1 |
| 825 |
1 m 2 r n 0 |
| 826 |
3 i i i 1 m 0</pre>
|
| 827 |
</div></div> |
| 828 |
<div class="paragraph"><p>The first line is a version identifier. |
| 829 |
In this example, all instances of the <em>2</em> character sequence <em>'</em>' will |
| 830 |
<strong>always</strong> be replaced by the <em>1</em> character sequence <em>"</em>; a <em>1</em> character |
| 831 |
sequence <em>m</em> <strong>may</strong> be replaced by the <em>2</em> character sequence <em>rn</em>, and |
| 832 |
the <em>3</em> character sequence <strong>may</strong> be replaced by the <em>1</em> character |
| 833 |
sequence <em>m</em>.</p></div> |
| 834 |
<div class="paragraph"><p>Version 3.03 and on supports a new, simpler format for the unicharambigs |
| 835 |
file:</p></div> |
| 836 |
<div class="literalblock"> |
| 837 |
<div class="content monospaced"> |
| 838 |
<pre>v2
|
| 839 |
'' " 1 |
| 840 |
m rn 0 |
| 841 |
iii m 0</pre>
|
| 842 |
</div></div> |
| 843 |
<div class="paragraph"><p>In this format, the "error" and "correction" are simple UTF-8 strings |
| 844 |
separated by a space, and, after another space, the same type specifier |
| 845 |
as v1 (0 for optional and 1 for mandatory substitution). Note the downside |
| 846 |
of this simpler format is that Tesseract has to encode the UTF-8 strings |
| 847 |
into the components of the unicharset. In complex scripts, this encoding |
| 848 |
may be ambiguous. In this case, the encoding is chosen such as to use the |
| 849 |
least UTF-8 characters for each component, ie the shortest unicharset |
| 850 |
components will make up the encoding.</p></div> |
| 851 |
</div>
|
| 852 |
</div>
|
| 853 |
<div class="sect1"> |
| 854 |
<h2 id="_history">HISTORY</h2> |
| 855 |
<div class="sectionbody"> |
| 856 |
<div class="paragraph"><p>The unicharambigs file first appeared in Tesseract 3.00; prior to that, a |
| 857 |
similar format, called DangAmbigs (<em>dangerous ambiguities</em>) was used: the |
| 858 |
format was almost identical, except only mandatory replacements could be |
| 859 |
specified, and field 5 was absent.</p></div> |
| 860 |
</div>
|
| 861 |
</div>
|
| 862 |
<div class="sect1"> |
| 863 |
<h2 id="_bugs">BUGS</h2> |
| 864 |
<div class="sectionbody"> |
| 865 |
<div class="paragraph"><p>This is a documentation "bug": it’s not currently clear what should be done |
| 866 |
in the case of ligatures (such as <em>fi</em>) which may also appear as regular |
| 867 |
letters in the unicharset.</p></div> |
| 868 |
</div>
|
| 869 |
</div>
|
| 870 |
<div class="sect1"> |
| 871 |
<h2 id="_see_also">SEE ALSO</h2> |
| 872 |
<div class="sectionbody"> |
| 873 |
<div class="paragraph"><p>tesseract(1), unicharset(5) |
| 874 |
<a href="https://tesseract-ocr.github.io/tessdoc/Training-Tesseract-3.03%E2%80%933.05.html#the-unicharambigs-file">https://tesseract-ocr.github.io/tessdoc/Training-Tesseract-3.03%E2%80%933.05.html#the-unicharambigs-file</a></p></div> |
| 875 |
</div>
|
| 876 |
</div>
|
| 877 |
<div class="sect1"> |
| 878 |
<h2 id="_author">AUTHOR</h2> |
| 879 |
<div class="sectionbody"> |
| 880 |
<div class="paragraph"><p>The Tesseract OCR engine was written by Ray Smith and his research groups |
| 881 |
at Hewlett Packard (1985-1995) and Google (2006-present).</p></div> |
| 882 |
</div>
|
| 883 |
</div>
|
| 884 |
</div>
|
| 885 |
<div id="footnotes"><hr></div> |
| 886 |
<div id="footer"> |
| 887 |
<div id="footer-text"> |
| 888 |
Last updated |
| 889 |
2020-02-06 21:45:54 CET |
| 890 |
</div>
|
| 891 |
</div>
|
| 892 |
</body>
|
| 893 |
</html>
|
