Mercurial > hg > mpdl-group

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0//EN">
<html>
  <head>
    <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
    <title>Max Planck Institute for the History of Science - Language technology services</title>
  </head>
<body>
<table align="right">
<tr>
<td>
  [<i>This software is dedicated to <a href="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/info.xql?info=malcolm">Dr. Malcolm Hyman</a></i>]
  <img src="/mpiwg-mpdl-cms-web/images/info.png" width="15" height="15" border="0" alt="Info"/><br/>
  [<i>It is based on <a href="http://archimedes.fas.harvard.edu/">Donatus and Pollux</a></i>]
  <img src="/mpiwg-mpdl-cms-web/images/info.png" width="15" height="15" border="0" alt="Info"/>
</td>
</tr>
</table>
<h2>Max Planck Institute for the History of Science - Language technology services</h2>

<ul>
  <li><b>Url: /mpiwg-mpdl-cms-web/lt/GetDictionaryEntries</b>
    <ul>
      <li>Request parameters
        <ul>
          <li>query (required)
              <ul>
                <li>by one form or lemma (e.g. "revolution")</li>
                <li>by a list of forms or lemmas (e.g. "revolution equality brotherliness")</li>
                <li>by a prefix range: entries starting with a prefix (e.g. "a*")</li>
             </ul>
          </li>
          <li>queryDisplay (optional)
            <ul>
              <li>display of the query</li>
              <li>default: content of parameter "query"</li>
            </ul>
          </li>
          <li>inputType (optional)
            <ul>
              <li>"form"</li>
              <li>"lemma"</li>
              <li>default: "form"</li>
            </ul>
          </li>
          <li>language (optional)
            <ul>
              <li>ISO 639-3 specifier</li>
              <li>default: "eng"</li>
            </ul>
          </li>
          <li>dictionary (optional)
            <ul>
              <li>dictionary name, e.g. "webster"</li>
              <li>default: "all" (all dictionaries for the specified language)</li>
            </ul>
          </li>
          <li>outputType (optional)
            <ul>
              <li>this parameter can occur many times (e.g. "outputType=morphCompact&amp;outputType=dictCompact")
                <ul>
                  <li>"morphCompact"</li>
                  <li>"dictCompact"</li>
                  <li>"wikiCompact"</li>
                  <li>"allCompact" (all output types compact)</li>
                  <li>"morphFull"</li>
                  <li>"dictFull"</li>
                  <li>"wikiFull"</li>
                  <li>"allFull" (all output types full)</li>
                </ul>
              </li>
              <li>default: "allCompact"</li>
            </ul>
          </li>
          <li>outputFormat (optional)
            <ul>
              <li>"html"</li>
              <li>"xml"</li>
              <li>default: "xml"</li>
            </ul>
          </li>
          <li>normalization (optional)
            <ul>
              <li>"none"</li>
              <li>"norm"</li>
              <li>default: "norm"</li>
            </ul>
          </li>
          <li>resultPageNumber (optional)
            <ul>
              <li>works only for range queries</li>
              <li>page number of the result (e.g. "2": result entries from position 51 to 100)</li>
              <li>default: "1"</li>
            </ul>
          </li>
          <li>resultPageSize (optional)
            <ul>
              <li>works only for range queries</li>
              <li>page size of the result (e.g. "100": each result page has a size of 100)</li>
              <li>default: "50"</li>
            </ul>
          </li>
        </ul>
      </li>
      <li>Response output
        <ul>
          <li>dependent of outputFormat, outputType and resultPage: morphology, dictionary and Wikipedia entries in Xml or Html format</li>
          <li>Example: <a href="lt/GetDictionaryEntries?query=a*&language=lat&outputFormat=html">query=a*&amp;language=lat&amp;outputFormat=html</a></li>
          <li>Example: <a href="lt/GetDictionaryEntries?query=a*&dictionary=ls">query=a*&amp;dictionary=ls</a></li>
          <li>Example: <a href="lt/GetDictionaryEntries?query=revolution&language=eng">query=revolution&amp;language=lat</a></li>
          <li>Example: <a href="lt/GetDictionaryEntries?query=multa&language=lat&outputFormat=html&outputType=allCompact">query=multa&amp;language=lat&amp;outputFormat=html&amp;outputType=allCompact</a></li>
        </ul>
      </li>
    </ul>
  </li>

  <li><b>Url: /mpiwg-mpdl-cms-web/lt/GetLemmas</b>
    <ul>
      <li>Request parameters
        <ul>
          <li>query (required)
              <ul>
                <li>one form or lemma (e.g. "revolution") or</li>
                <li>blank separated list of forms or lemmas (e.g. "revolution equality brotherliness")</li>
             </ul>
          </li>
          <li>inputType (optional)
            <ul>
              <li>"form"</li>
              <li>"lemma"</li>
              <li>default: "form"</li>
            </ul>
          </li>
          <li>language (optional)
            <ul>
              <li>ISO 639-3 specifier</li>
              <li>default: "eng"</li>
            </ul>
          </li>
          <li>outputType (optional)
            <ul>
              <li>"compact"</li>
              <li>"full"</li>
              <li>default: "compact"</li>
            </ul>
          </li>
          <li>outputFormat (optional)
            <ul>
              <li>"html"</li>
              <li>"xml"</li>
              <li>"string" (lemma names separated by a blank)</li>
              <li>default: "xml"</li>
            </ul>
          </li>
          <li>normalization (optional)
            <ul>
              <li>"none"</li>
              <li>"norm"</li>
              <li>default: "norm"</li>
            </ul>
          </li>
        </ul>
      </li>
      <li>Response output
        <ul>
          <li>dependent of outputFormat and outputType: lemma entries in Xml or Html or string format</li>
          <li>Example: <a href="lt/GetLemmas?query=multa&language=lat&outputFormat=html">query=multa&amp;language=lat&amp;outputFormat=html</a></li>
        </ul>
      </li>
    </ul>
  </li>

  <li><b>Url: /mpiwg-mpdl-cms-web/lt/GetForms</b>
    <ul>
      <li>Request parameters
        <ul>
          <li>query (required)
              <ul>
                <li>one lemma (e.g. "revolution") or</li>
                <li>blank separated list of forms (e.g. "revolution equality brotherliness")</li>
             </ul>
          </li>
          <li>language (optional)
            <ul>
              <li>ISO 639-3 specifier</li>
              <li>default: "eng"</li>
            </ul>
          </li>
          <li>outputType (optional)
            <ul>
              <li>"compact"</li>
              <li>"full"</li>
              <li>default: "compact"</li>
            </ul>
          </li>
          <li>outputFormat (optional)
            <ul>
              <li>"html"</li>
              <li>"xml"</li>
              <li>"string" (lemma names separated by a blank)</li>
              <li>default: "xml"</li>
            </ul>
          </li>
          <li>normalization (optional)
            <ul>
              <li>"none"</li>
              <li>"norm"</li>
              <li>default: "norm"</li>
            </ul>
          </li>
        </ul>
      </li>
      <li>Response output
        <ul>
          <li>dependent of outputFormat and outputType: form entries in Xml or Html or string format</li>
          <li>Example: <a href="lt/GetForms?query=edo sum&language=lat&outputFormat=string">query=edo sum&amp;language=lat&amp;outputFormat=string</a></li>
        </ul>
      </li>
    </ul>
  </li>

  <li><b>Url: /mpiwg-mpdl-cms-web/text/Tokenize</b>
    <ul>
      <li>Request parameters
        <ul>
          <li>inputString or srcUrl (required)
            <ul>
              <li>inputString
                <ul>
                  <li>string which should be tokenized
                    <ul>
                      <li>unstructured text</li>
                      <li>XML fragment/document</li>
                    </ul>
                  </li>
                </ul>
              </li>
              <li>srcUrl
                <ul>
                  <li>source URL
                    <ul>
                      <li>unstructured text</li>
                      <li>XML fragment/document</li>
                    </ul>
                  </li>
                </ul>
              </li>
            </ul>
          </li>
          <li>language (optional)
            <ul>
              <li>ISO 639-3 specifier</li>
              <li>if input is XML and an element contains the attribute "xml:lang" this value is used for this element</li>
              <li>default: "eng"</li>
            </ul>
          </li>
          <li>normalization (optional)
            <ul>
              <li>"none" (no normalization)</li>
              <li>"reg" (regularized)</li>
              <li>"norm" (regularized + normalized)</li>
              <li>default: "norm"</li>
            </ul>
          </li>
          <li>normalizationType (optional)
            <ul>
              <li>"dictionary"</li>
              <li>"display"</li>
              <li>default: "dictionary"</li>
            </ul>
          </li>
          <li>elements (optional)
            <ul>
              <li>list of xml element names which should be tokenized (e.g. "s head")</li>
              <li>default: empty list (which means: all elements are tokenized)</li>
            </ul>
          </li>
          <li>stopElements (optional)
            <ul>
              <li>list of xml element names which are stop elements(e.g. "var emph"): stop elements: its tokens should not get word tags (when output format is "xml") or its tokens should be removed (if output format is "string")</li>
              <li>default: empty list</li>
            </ul>
          </li>
          <li>highlightTerms (optional)
            <ul>
              <li>list of word forms which should be highlighted. Each matched word form is surrounded by &lt;hi&gt;&lt;/hi&gt;. The matching function is dependent of the normalization. E.g. if normalization = "norm" then the normalized word form is fetched and highlighted.</li>
              <li>default: empty list</li>
            </ul>
          </li>
          <li>outputFormat (optional)
            <ul>
              <li>"xml"</li>
              <li>"string"</li>
              <li>default: "xml"</li>
            </ul>
          </li>
          <li>outputOptions (optional)
            <ul>
              <li>output options separated by blanks (e.g. "withForms withLemmas")
                <ul>
                  <li>"withForms"</li>
                  <li>"withLemmas"</li>
                  <li>default: empty list</li>
                </ul>
              </li>
            </ul>
          </li>
        </ul>
      </li>
      <li>Response output
        <ul>
          <li>outputFormat=xml
            <ul>
              <li>tokenized inputString or document (enriched by element &lt;w&gt;)
                <ul>
                  <li>Example: &lt;s&gt;&lt;w lang="deu" form="dies" formRegularized="dies" formNormalized="dies" forms="dies, dieser, dieses, diesen" lemmas="dieser"&gt;Dies&lt;/w&gt; &lt;w
                  lang="deu" form="ist" formRegularized="ist" formNormalized="ist" forms="bin, bist, ist, seid, sind, sein, war, warst, wart" lemmas="sein"&gt;ist&lt;/w&gt; &lt;w
                  lang="deu" form="ein" formRegularized="ein" formNormalized="ein" forms="ein, eines, einer" lemmas="ein"&gt;ein&lt;/w&gt; &lt;w lang="deu" form="satz"
                  formRegularized="satz" formNormalized="satz" forms="satz, sätze, satzes" lemmas="satz"&gt;Satz&lt;/w&gt;&lt;/s&gt;
                  </li>
                </ul>
              </li>
            </ul>
          <li>outputFormat=string
            <ul>
              <li>word tokens of inputString or document (separated by Blank)</li>
            </ul>
          <li>Example: <a href="text/Tokenize?inputString=edo sum philoſophi&language=lat&outputFormat=xml">inputString=edo sum philoſophi&amp;language=lat&amp;outputFormat=xml</a></li>
          <li>Example: <a href="text/Tokenize?language=lat&srcUrl=http://mpdl-system.mpiwg-berlin.mpg.de/mpdl/page-query-result.xql?document=/echo/la/Benedetti_1585.xml%26mode=pureXml%26pn=13">language=lat&amp;srcUrl=http://mpdl-system.mpiwg-berlin.mpg.de/mpdl/page-query-result.xql?document=/echo/la/Benedetti_1585.xml%26mode=pureXml%26pn=13</a></li>
          <li>Example: <a href="text/Tokenize?language=lat&highlightTerms=eorumque&srcUrl=http://mpdl-system.mpiwg-berlin.mpg.de/mpdl/page-query-result.xql?document=/echo/la/Benedetti_1585.xml%26mode=pureXml%26pn=13">language=lat&amp;highlightTerms=eorumque&amp;srcUrl=http://mpdl-system.mpiwg-berlin.mpg.de/mpdl/page-query-result.xql?document=/echo/la/Benedetti_1585.xml%26mode=pureXml%26pn=13</a></li>
          <li>Example: <a href="text/Tokenize?language=lat&outputOptions=withForms withLemmas&srcUrl=http://mpdl-system.mpiwg-berlin.mpg.de/mpdl/page-query-result.xql?document=/echo/la/Benedetti_1585.xml%26mode=pureXml%26pn=13">language=lat&amp;outputOptions=withForms withLemmas&amp;srcUrl=http://mpdl-system.mpiwg-berlin.mpg.de/mpdl/page-query-result.xql?document=/echo/la/Benedetti_1585.xml%26mode=pureXml%26pn=13</a></li>
          <li>Example: <a href="text/Tokenize?language=lat&outputFormat=string&normalization=orig&srcUrl=http://mpdl-system.mpiwg-berlin.mpg.de/mpdl/page-query-result.xql?document=/echo/la/Benedetti_1585.xml%26mode=pureXml%26pn=13">language=lat&amp;outputFormat=string&amp;normalization=orig&amp;srcUrl=http://mpdl-system.mpiwg-berlin.mpg.de/mpdl/page-query-result.xql?document=/echo/la/Benedetti_1585.xml%26mode=pureXml%26pn=13</a></li>
          <li>Example: <a href="text/Tokenize?language=lat&outputFormat=string&outputOptions=withLemmas&srcUrl=http://mpdl-system.mpiwg-berlin.mpg.de/mpdl/page-query-result.xql?document=/echo/la/Benedetti_1585.xml%26mode=pureXml%26pn=13">language=lat&amp;outputFormat=string&amp;outputOptions=withLemmas&amp;srcUrl=http://mpdl-system.mpiwg-berlin.mpg.de/mpdl/page-query-result.xql?document=/echo/la/Benedetti_1585.xml%26mode=pureXml%26pn=13</a></li>
        </ul>
      </li>
    </ul>
  </li>

  <li><b>Url: /mpiwg-mpdl-cms-web/text/Normalize</b>
    <ul>
      <li>Request parameters
        <ul>
          <li>inputString (required)
            <ul>
              <li>string which should be normalized</li>
            </ul>
          </li>
          <li>language (optional)
            <ul>
              <li>ISO 639-3 specifier</li>
              <li>default: "eng"</li>
            </ul>
          </li>
          <li>type (optional)
            <ul>
              <li>"dictionary"</li>
              <li>"display"</li>
              <li>default: "display"</li>
            </ul>
          </li>
        </ul>
      </li>
      <li>Response output
        <ul>
          <li>normalized string</li>
          <li>Example: <a href="text/Normalize?inputString=philoſophi&language=lat">inputString=philoſophi&amp;language=lat</a></li>
        </ul>
      </li>
    </ul>
  </li>

  <li><b>Url: /mpiwg-mpdl-cms-web/text/Transcode</b>
    <ul>
      <li>Request parameters
        <ul>
          <li>inputString (required)
            <ul>
              <li>string which should be transcoded</li>
            </ul>
          </li>
          <li>srcEncoding (required)
            <ul>
              <li>"betacode"</li>
              <li>"buckwalter"</li>
              <li>"unicode"</li>
            </ul>
          </li>
          <li>destEncoding (optional)
            <ul>
              <li>"betacode"</li>
              <li>"buckwalter"</li>
              <li>"unicode"</li>
              <li>default: "unicode"</li>
            </ul>
          </li>
        </ul>
      </li>
      <li>Response output
        <ul>
          <li>transcoded string</li>
          <li>Example: <a href="text/Transcode?inputString=kai/&srcEncoding=betacode&destEncoding=unicode">inputString=kai/&amp;srcEncoding=betacode&amp;destEncoding=unicode</a></li>
        </ul>
      </li>
    </ul>
  </li>
</ul>


</body></html>
author	Josef Willenborg <jwillenborg@mpiwg-berlin.mpg.de>
date	Tue, 21 May 2013 10:19:32 +0200
parents
children