/usr/share/doc/htdig-doc/html/config.html is in htdig-doc 1:3.2.0b6-17.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 | <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd">
<html>
<head>
<title>
ht://Dig: Configuration
</title>
</head>
<body bgcolor="#eef7ff">
<h1>
Configuration
</h1>
<p>
ht://Dig Copyright © 1995-2004 <a href="THANKS.html">The ht://Dig Group</a><br>
Please see the file <a href="COPYING">COPYING</a> for
license information.
</p>
<hr size="4" noshade>
<p>
ht://Dig requires a configuration file and several HTML files
to operate correctly. Fortunately, when ht://Dig is
installed, a very reasonable configuration is created and in
most cases only minor modifications to the files are
necessary.
</p>
<p>
Below, we will use the variables that were set in CONFIG to
designate specific paths.
</p>
<p>
Standard files:
</p>
<ul>
<li>
<a href="#htdig.conf">${CONFIG_DIR}/htdig.conf</a>
</li>
<li>
<a href="#search.html">${SEARCH_DIR}/search.html</a>
</li>
<li>
<a href="#header.html">${COMMON_DIR}/header.html</a>
</li>
<li>
<a href="#footer.html">${COMMON_DIR}/footer.html</a>
</li>
<li>
<a href="#wrapper.html">${COMMON_DIR}/wrapper.html</a>
</li>
<li>
<a href="#nomatch.html">${COMMON_DIR}/nomatch.html</a>
</li>
<li>
<a href="#syntax.html">${COMMON_DIR}/syntax.html</a>
</li>
</ul>
<hr noshade>
<h2>
<a name="#htdig.conf">${CONFIG_DIR}/htdig.conf</a>
</h2>
<p>
This is the main runtime configuration file for all programs
that make up ht://Dig. The file is fully described in the
<a href="confindex.html" target="_top">Configuration file
manual</a>.
</p>
<p>
When ht://Dig is installed, several attributes will be
customized to your particular environment, but for reference,
here is a sample copy of what it can look like:
</p>
<pre>
<font size="-1">
#
# Example config file for ht://Dig.
#
# This configuration file is used by all the programs that make up ht://Dig.
# Please refer to the attribute reference manual for more details on what
# can be put into this file. (http://www.htdig.org/confindex.html)
# Note that most attributes have very reasonable default values so you
# really only have to add attributes here if you want to change the defaults.
#
# What follows are some of the common attributes you might want to change.
#
#
# Specify where the database files need to go. Make sure that there is
# plenty of free disk space available for the databases. They can get
# pretty big.
#
database_dir: /opt/www/htdig/db
#
# This specifies the URL where the robot (htdig) will start. You can specify
# multiple URLs here. Just separate them by some whitespace.
# The example here will cause the ht://Dig homepage and related pages to be
# indexed.
# You could also index all the URLs in a file like so:
# start_url: `${common_dir}/start.url`
#
start_url: http://www.htdig.org/
#
# This attribute limits the scope of the indexing process. The default is to
# set it to the same as the start_url above. This way only pages that are on
# the sites specified in the start_url attribute will be indexed and it will
# reject any URLs that go outside of those sites.
#
# Keep in mind that the value for this attribute is just a list of string
# patterns. As long as URLs contain at least one of the patterns it will be
# seen as part of the scope of the index.
#
limit_urls_to: ${start_url}
#
# If there are particular pages that you definitely do NOT want to index, you
# can use the exclude_urls attribute. The value is a list of string patterns.
# If a URL matches any of the patterns, it will NOT be indexed. This is
# useful to exclude things like virtual web trees or database accesses. By
# default, all CGI URLs will be excluded. (Note that the /cgi-bin/ convention
# may not work on your web server. Check the path prefix used on your web
# server.)
#
exclude_urls: /cgi-bin/ .cgi
#
# Since ht://Dig does not (and cannot) parse every document type, this
# attribute is a list of strings (extensions) that will be ignored during
# indexing. These are *only* checked at the end of a URL, whereas
# exclude_url patterns are matched anywhere.
#
# Also keep in mind that while other attributes allow regex, these must be
# actual strings.
#
bad_extensions: .wav .gz .z .sit .au .zip .tar .hqx .exe .com .gif \
.jpg .jpeg .aiff .class .map .ram .tgz .bin .rpm .mpg .mov .avi .css
#
# The string htdig will send in every request to identify the robot. Change
# this to your email address.
#
maintainer: unconfigured@htdig.searchengine.maintainer
#
# The excerpts that are displayed in long results rely on stored information
# in the index databases. The compiled default only stores 512 characters of
# text from each document (this excludes any HTML markup...) If you plan on
# using the excerpts you probably want to make this larger. The only concern
# here is that more disk space is going to be needed to store the additional
# information. Since disk space is cheap (! :-)) you might want to set this
# to a value so that a large percentage of the documents that you are going
# to be indexing are stored completely in the database. At SDSU we found
# that by setting this value to about 50k the index would get 97% of all
# documents completely and only 3% was cut off at 50k. You probably want to
# experiment with this value.
# Note that if you want to set this value low, you probably want to set the
# excerpt_show_top attribute to false so that the top excerpt_length characters
# of the document are always shown.
#
max_head_length: 10000
#
# To limit network connections, ht://Dig will only pull up to a certain limit
# of bytes. This prevents the indexing from dying because the server keeps
# sending information. However, several FAQs happen because people have files
# bigger than the default limit of 100KB. This sets the default a bit higher.
# (see <http://www.htdig.org/FAQ.html> for more)
#
max_doc_size: 200000
#
# Most people expect some sort of excerpt in results. By default, if the
# search words aren't found in context in the stored excerpt, htsearch shows
# the text defined in the no_excerpt_text attribute:
# (None of the search words were found in the top of this document.)
# This attribute instead will show the top of the excerpt.
#
no_excerpt_show_top: true
#
# Depending on your needs, you might want to enable some of the fuzzy search
# algorithms. There are several to choose from and you can use them in any
# combination you feel comfortable with. Each algorithm will get a weight
# assigned to it so that in combinations of algorithms, certain algorithms get
# preference over others. Note that the weights only affect the ranking of
# the results, not the actual searching.
# The available algorithms are:
# accents
# exact
# endings
# metaphone
# prefix
# regex
# soundex
# speling [sic]
# substring
# synonyms
# By default only the "exact" algorithm is used with weight 1.
# Note that if you are going to use the endings, metaphone, soundex, accents,
# or synonyms algorithms, you will need to run htfuzzy to generate
# the databases they use.
#
search_algorithm: exact:1 synonyms:0.5 endings:0.1
#
# The following are the templates used in the builtin search results
# The default is to use compiled versions of these files, which produces
# slightly faster results. However, uncommenting these lines makes it
# very easy to change the format of search results.
# See <http://www.htdig.org/hts_templates.html> for more details.
#
# template_map: Long long ${common_dir}/long.html \
# Short short ${common_dir}/short.html
# template_name: long
#
# The following are used to change the text for the page index.
# The defaults are just boring text numbers. These images spice
# up the result pages quite a bit. (Feel free to do whatever, though)
#
next_page_text: <img src="/htdig/buttonr.gif" border="0" align="middle" width="30" height="30" alt="next">
no_next_page_text:
prev_page_text: <img src="/htdig/buttonl.gif" border="0" align="middle" width="30" height="30" alt="prev">
no_prev_page_text:
page_number_text: '<img src="/htdig/button1.gif" border="0" align="middle" width="30" height="30" alt="1">' \
'<img src="/htdig/button2.gif" border="0" align="middle" width="30" height="30" alt="2">' \
'<img src="/htdig/button3.gif" border="0" align="middle" width="30" height="30" alt="3">' \
'<img src="/htdig/button4.gif" border="0" align="middle" width="30" height="30" alt="4">' \
'<img src="/htdig/button5.gif" border="0" align="middle" width="30" height="30" alt="5">' \
'<img src="/htdig/button6.gif" border="0" align="middle" width="30" height="30" alt="6">' \
'<img src="/htdig/button7.gif" border="0" align="middle" width="30" height="30" alt="7">' \
'<img src="/htdig/button8.gif" border="0" align="middle" width="30" height="30" alt="8">' \
'<img src="/htdig/button9.gif" border="0" align="middle" width="30" height="30" alt="9">' \
'<img src="/htdig/button10.gif" border="0" align="middle" width="30" height="30" alt="10">'
#
# To make the current page stand out, we will put a border around the
# image for that page.
#
no_page_number_text: '<img src="/htdig/button1.gif" border="2" align="middle" width="30" height="30" alt="1">' \
'<img src="/htdig/button2.gif" border="2" align="middle" width="30" height="30" alt="2">' \
'<img src="/htdig/button3.gif" border="2" align="middle" width="30" height="30" alt="3">' \
'<img src="/htdig/button4.gif" border="2" align="middle" width="30" height="30" alt="4">' \
'<img src="/htdig/button5.gif" border="2" align="middle" width="30" height="30" alt="5">' \
'<img src="/htdig/button6.gif" border="2" align="middle" width="30" height="30" alt="6">' \
'<img src="/htdig/button7.gif" border="2" align="middle" width="30" height="30" alt="7">' \
'<img src="/htdig/button8.gif" border="2" align="middle" width="30" height="30" alt="8">' \
'<img src="/htdig/button9.gif" border="2" align="middle" width="30" height="30" alt="9">' \
'<img src="/htdig/button10.gif" border="2" align="middle" width="30" height="30" alt="10">'
</font>
</pre>
<hr noshade>
<h2>
<a name="search.html">${SEARCH_DIR}/search.html</a>
</h2>
<p>
This is the default search form. It is an example interface to
the search engine, htsearch. The file contains a form with as
its action a call to htsearch. There are several form variables
which htsearch will use. More about those can be found in the
<a href="htsearch.html" target="_top">htsearch
documentation</a>.
</p>
<p>
An example file can be as follows:
</p>
<pre>
<font size="-1">
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<html>
<head>
<title>ht://Dig WWW Search</title>
</head>
<body bgcolor="#eef7ff">
<h1>
<a href="http://www.htdig.org"><IMG SRC="/htdig/htdig.gif" align="bottom" alt="ht://Dig" border="0"></a>
WWW Site Search</h1>
<hr noshade size="4">
This search will allow you to search the contents of
all the publicly available WWW documents at this site.
<br>
<p>
<form method="post" action="/cgi-bin/htsearch">
<font size="-1">
Match: <select name="method">
<option value="and">All
<option value="or">Any
<option value="boolean">Boolean
</select>
Format: <select name="format">
<option value="builtin-long">Long
<option value="builtin-short">Short
</select>
Sort by: <select name="sort">
<option value="score">Score
<option value="time">Time
<option value="title">Title
<option value="revscore">Reverse Score
<option value="revtime">Reverse Time
<option value="revtitle">Reverse Title
</select>
</font>
<input type="hidden" name="config" value="htdig">
<input type="hidden" name="restrict" value="">
<input type="hidden" name="exclude" value="">
<br>
Search:
<input type="text" size="30" name="words" value="">
<input type="submit" value="Search">
</form>
<hr noshade size="4">
</body>
</html>
</font>
</pre>
<hr noshade>
<h2>
<a name="header.html">${COMMON_DIR}/header.html</a>
</h2>
<p>
This file is the file that is output before any of the search
results are produced in a search. This file can be customized
to reflect your particular web look-and-feel, for example. Take
note that this file is only the top part of the full HTML
document that is produced when search results are displayed.
This means that it should start with the proper HTML
introductory tags and title.
</p>
<p>
This file will not just simply be copied. Instead, the search
engine will look for special variables inside the file. These
variables will be replaced with the appropriate values for
the particular search it is used for. For more details of the
use of these variables, consult the
<a href="hts_templates.html">htsearch templates</a> documentation.
</p>
<p>
Below is the default header.html file that gets installed.
Note that it contains a form to allow the user to refine the
search.
</p>
<pre>
<font size="-1">
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<html><head><title>Search results for '$&(WORDS)'</title></head>
<body bgcolor="#eef7ff">
<h2><img src="/htdig/htdig.gif" alt="ht://Dig">
Search results for '$&(LOGICAL_WORDS)'</h2>
<hr noshade size="4">
<form method="get" action="$(CGI)">
<font size="-1">
<input type="hidden" name="config" value="$&(CONFIG)">
<input type="hidden" name="restrict" value="$&(RESTRICT)">
<input type="hidden" name="exclude" value="$&(EXCLUDE)">
Match: $(METHOD)
Format: $(FORMAT)
Sort by: $(SORT)
<br>
Refine search:
<input type="text" size="30" name="words" value="$&(WORDS)">
<input type="submit" value="Search">
</font>
</form>
<hr noshade size="1">
<strong>Documents $(FIRSTDISPLAYED) - $(LASTDISPLAYED) of $(MATCHES) matches.
More <img src="/htdig/star.gif" alt="*">'s indicate a better match.
</strong>
<hr noshade size="1">
</font>
</pre>
<hr noshade>
<h2>
<a name="footer.html">${COMMON_DIR}/footer.html</a>
</h2>
<p>
This file is output after all the search results have been
displayed. All the same header.html rules apply to this file,
except that it is supposed to contain all the ending HTML tags.
</p>
<p>
Below is the default footer.html file that gets installed.
Note that it contains the page navigation stuff.
</p>
<pre>
<font size="-1">
$(PAGEHEADER)
$(PREVPAGE) $(PAGELIST) $(NEXTPAGE)
<hr noshade size="4">
<a href="http://www.htdig.org/">
<img src="/htdig/htdig.gif" border="0" alt="ht://Dig">ht://Dig $(VERSION)</a>
</body></html>
</font>
</pre>
<hr noshade>
<h2>
<a name="wrapper.html">${COMMON_DIR}/wrapper.html</a>
</h2>
<p>
This file may be used in place of the header.html and footer.html
files above. It is simply the concatenation of these two files,
with the pseudo-variable <strong>$(HTSEARCH_RESULTS)</strong> as
a separator for the header and footer sections.
All the same header.html and footer.html rules apply to this file.
To make this file override the header and footer files above, you
must define the <a href="attrs.html#search_results_wrapper">
search_results_wrapper</a> attribute.
</p>
<hr noshade>
<h2>
<a name="nomatch.html">${COMMON_DIR}/nomatch.html</a>
</h2>
<p>
If a search produces no matches, this file is displayed. All
the relevant variables will be replaced as in the header.html
and footer.html files. The default nomatch.html is little more
than header.html and footer.html appended:
</p>
<pre>
<font size="-1">
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<html><head><title>No match for '$&(LOGICAL_WORDS)'</title></head>
<body bgcolor="#eef7ff">
<h1><img src="/htdig/htdig.gif" alt="ht://Dig">
Search results</h1>
<hr noshade size="4">
<h2>No matches were found for '$&(LOGICAL_WORDS)'</h2>
<p>
Check the spelling of the search word(s) you used.
If the spelling is correct and you only used one word,
try using one or more similar search words with "<strong>Any</strong>."
</p><p>
If the spelling is correct and you used more than one
word with "<strong>Any</strong>," try using one or more similar search
words with "<strong>Any</strong>."</p><p>
If the spelling is correct and you used more than one
word with "<strong>All</strong>," try using one or more of the same words
with "<strong>Any</strong>."</p>
<hr noshade size="4">
<form method="get" action="$(CGI)">
<font size="-1">
<input type="hidden" name="config" value="$&(CONFIG)">
<input type="hidden" name="restrict" value="$&(RESTRICT)">
<input type="hidden" name="exclude" value="$&(EXCLUDE)">
Match: $(METHOD)
Format: $(FORMAT)
Sort by: $(SORT)
<br>
Refine search:
<input type="text" size="30" name="words" value="$&(WORDS)">
<input type="submit" value="Search">
</font>
</form>
<hr noshade size="4">
<a href="http://www.htdig.org/">
<img src="/htdig/htdig.gif" border="0" alt="ht://Dig">ht://Dig $(VERSION)</a>
</body></html>
</font>
</pre>
<hr noshade>
<h2>
<a name="syntax.html">${COMMON_DIR}/syntax.html</a>
</h2>
<p>
If a boolean expression search causes a syntax error, this file
will be displayed.
</p>
<pre>
<font size="-1">
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<html><head><title>Error in Boolean search for '$&(WORDS)'</title></head>
<body bgcolor="#eef7ff">
<h1><img src="/htdig/htdig.gif" alt="ht://Dig">
Error in Boolean search for '$&(LOGICAL_WORDS)'</h1>
<hr noshade size="4">
Boolean expressions need to be 'correct' in order for the search
system to use them.
The expression you entered has errors in it.<p>
Examples of correct expressions are: <strong>cat and dog</strong>, <strong>cat
not dog</strong>, <strong>cat or (dog not nose)</strong>.<br>Note that
the operator <strong>not</strong> has the meaning of 'without'.
<blockquote><strong>
$(SYNTAXERROR)
</strong></blockquote>
<hr noshade size="4">
<form method="get" action="$(CGI)">
<font size="-1">
<input type="hidden" name="config" value="$&(CONFIG)">
<input type="hidden" name="restrict" value="$&(RESTRICT)">
<input type="hidden" name="exclude" value="$&(EXCLUDE)">
Match: $(METHOD)
Format: $(FORMAT)
Sort: $(SORT)
<br>
Refine search:
<input type="text" size="30" name="words" value="$&(WORDS)">
<input type="submit" value="Search">
</font>
</form>
<hr noshade size="4">
<a href="http://www.htdig.org/">
<img src="/htdig/htdig.gif" border="0" alt="ht://Dig">ht://Dig $(VERSION)</a>
</body></html>
</font>
</pre>
<hr size="4" noshade>
Last modified: $Date: 2004/05/28 13:15:18 $
</body>
</html>
|