Page History

...

Fuzzy search

Purpose

Returns enrties\translations with small differences from requested

Request

POST /%service%/%tm_name%/fuzzysearch

Params

Required: source, sourceLang, targetLang

iNumOfProposal - limit of found proposals - max is 20, if 0 → use default value '5'

Code Block

language	js
title	Response
collapse	true

Request example:


Request example:
{ // required fields
  "sourceLang":"en-GB",    
     // langs would be checked with languages.xml 
  "targetLang":"de",   
   "source":"For > 100 setups.", 

 // optional fields  
  ["documentName":"OBJ_DCL-0000000845-004_pt-br.xml"],   
  ["segmentNumber":""15],   
  ["markupTable":"OTMXUXLF"],    
  //if there is no markup, default OTMXUXLF would be used. 
								 //Markup tables should be located inside ~/.t5memory/TABLE/%markup$.TBL 
  ["context":"395_408"],  
  ["numOfProposals":20],   // num of expected segments in output. By default it's 5
  ["loggingThreshold": 0]
}





Response example:

Success:
{
  "ReturnValue": 0,
  "ErrorMsg": "",
  "NumOfFoundProposals": 1, 
  "results": [
  {
     "source": "For > 100 setups.",
     "target": "Für > 100 Aufstellungen.",
     "segmentNumber": 10906825,
     "id": "",
     "documentName": "none",
    "documentShortName": "NONE",
    "sourceLang": "en-GB",
    "targetLang": "de-DE",
    "type": "Manual",
    "matchType": "Exact", // could be exact or fuzzy
    "author": "",
    "timestamp": "20190401T084052Z",
    "matchRate": 100,
       "markupTablefuzzyWords": "OTMXML",
    "context": "",
   "additionalInfo": ""
   }
 ]
}

Not -1, // for exact match it would be -1 here and in diffs
     "fuzzyDiffs": -1, // otherwise here would be amount of parsed words and diffs that was 
					   // used in fuzzy matchrate calculation    
	 "markupTable": "OTMXML",
     "context": "",
     "additionalInfo": ""
   }
 ]
}

Not found:

{
"ReturnValue": 133,
"ErrorMsg": "OtmMemoryServiceWorker::concordanceSearch::"
}
For exact match used function that's comparing strings ignoring whitespaces. First normalized strings(without tags).
If it's the same string, then t5memory is checking string with tags and could return 100 or 97 match rate depending on result.

Then it's checking context match rate and if document name is the same(non case sensitive)

Then it's checking and modifying exactMatchRate according to code in code block below.

Code Block

language	js
title	Response
collapse	true

ExactMatchRate calculation:so, before usExact is equal to 97 or 100, depending if strings with tags are equal ignoring whitespaces  and then code do some tweaks.
 pClb is struct that have proposals from TM, pGetIn is fuzzy requests data

 // loop over CLBs and look for best matching entry
{
  LONG lLeftClbLen; // left CLB entries in CLB list
  PTMX_TARGET_CLB pClb; // pointer for CLB list processing
  #define SEG_DOC_AND_CONTEXT_MATCH 8
  #define DOC_AND_CONTEXT_MATCH 7
  #define CONTEXT_MATCH 6
  #define SAME_SEG_AND_DOC_MATCH 5
  #define SAME_DOC_MATCH 4
  #define MULT_DOC_MATCH 3
  #define NORMAL_MATCH 2
  #define IGNORE_MATCH 1
  SHORT sCurMatch = 0;

  // loop over all target CLBs
  pClb = pTMXTargetClb;
  lLeftClbLen = RECLEN(pTMXTargetRecord) -
  pTMXTargetRecord->usClb;
  while ( ( lLeftClbLen > 0 ) && (sCurMatch < SAME_SEG_AND_DOC_MATCH) )
  {
    USHORT usTranslationFlag = pClb->bTranslationFlag;
    USHORT usCurContextRanking = 0; // context ranking of this match
    BOOL fIgnoreProposal = FALSE;
    // apply global memory option file on global memory proposals
   if ( pClb->bTranslationFlag == TRANSLFLAG_GLOBMEM ) // pClb it's segment in TM
   {
       if ( (pGetIn->pvGMOptList != NULL) && pClb->usAddDataLen ) // pGetIn it's fuzzy requests segment
       {

           USHORT usAddDataLen = NtmGetAddData( pClb, ADDDATA_ADDINFO_ID, pContextBuffer, MAX_SEGMENT_SIZE );
           if ( usAddDataLen )
           {
               GMMEMOPT GobMemOpt = GlobMemGetFlagForProposal( pGetIn->pvGMOptList, pContextBuffer );
               switch ( GobMemOpt )
               {
                  case GM_SUBSTITUTE_OPT: usTranslationFlag = TRANSLFLAG_NORMAL; break;
                  case GM_HFLAG_OPT : usTranslationFlag = TRANSLFLAG_GLOBMEM; break;
                  case GM_HFLAGSTAR_OPT : usTranslationFlag = TRANSLFLAG_GLOBMEMSTAR; break;
                  case GM_EXCLUDE_OPT : fIgnoreProposal = TRUE; break;
               } /* endswitch */
          } /* endif */
     } /* endif */ 

     if ( pClb == pTMXTargetClb )
    {
       usTargetTranslationFlag = usTranslationFlag;
    } /* endif *
  } /* endif */ 


  // check context strings (if any)
  if ((!fIgnoreProposal)
       && pGetIn->szContext[0]
       && pClb->usAddDataLen )
   {
       USHORT usContextLen = NtmGetAddData( pClb, ADDDATA_CONTEXT_ID, pContextBuffer, MAX_SEGMENT_SIZE );
       if ( usContextLen != 0 )
       {
            usCurContextRanking = NTMCompareContext( pTmClb, pGetIn->szTagTable, pGetIn->szContext, pContextBuffer );
       } /* endif */
    } /* endif */


  // check for matching document names
  if ( pGetIn->ulParm & GET_IGNORE_PATH )
  {
     // we have to compare the real document names rather than comparing the document name IDs
     PSZ pszCLBDocName = NTMFindNameForID( pTmClb, &(pClb->usFileId), (USHORT)FILE_KEY );
     if ( pszCLBDocName != NULL )
     {
        PSZ pszName = UtlGetFnameFromPath( pszCLBDocName );
        if ( pszName == NULL )
        {
           pszName = pszCLBDocName;
         } /* endif */
      fMatchingDocName = stricmp( pszName, pszDocName ) == 0;
    }
    else
    {
       // could not access the document name, we have to compare the document name IDs
      fMatchingDocName = ((pClb->usFileId == usGetFile) || (pClb->usFileId == usAlternateGetFile));
    } /* endif */
  }
  else
  {
     // we can compare the document name IDs
     fMatchingDocName = ((pClb->usFileId == usGetFile) || (pClb->usFileId == usAlternateGetFile));
  } /* endif */


  if ( fIgnoreProposal )
  {
    if ( sCurMatch == 0 )
    {
      sCurMatch = IGNORE_MATCH;
    } /* endif */
  }
  else if ( usCurContextRanking == 100 )
  {
    if ( fMatchingDocName && (pClb->ulSegmId >= (pGetIn->ulSegmentId - 1)) && (pClb->ulSegmId <= (pGetIn->ulSegmentId + 1)) )
    {
      if ( sCurMatch < SEG_DOC_AND_CONTEXT_MATCH )
      {
         sCurMatch = SEG_DOC_AND_CONTEXT_MATCH;
        pTMXTargetClb = pClb; // use this target CLB for match
        usTargetTranslationFlag = usTranslationFlag;
        usContextRanking = usCurContextRanking;
      }
    }
    else if ( fMatchingDocName )
    {
    if ( sCurMatch < DOC_AND_CONTEXT_MATCH )
    {
      sCurMatch = DOC_AND_CONTEXT_MATCH;
      pTMXTargetClb = pClb; // use this target CLB for match
      usTargetTranslationFlag = usTranslationFlag;
      usContextRanking = usCurContextRanking;
     }
     else if ( sCurMatch == DOC_AND_CONTEXT_MATCH )
     {
       // we have already a match of this type so check if context ranking
       if ( usCurContextRanking > usContextRanking )
       {
          pTMXTargetClb = pClb; // use newer target CLB for match
          usTargetTranslationFlag = usTranslationFlag;
          usContextRanking = usCurContextRanking;
       }
       // use time info to ensure that latest match is used
       else if ( usCurContextRanking == usContextRanking )
       {
         // GQ 2015-04-10 New approach: If we have an exact-exact match use this one, otherwise use timestamp for the comparism
         BOOL fExactExactNewCLB = fMatchingDocName && (pClb->ulSegmId >= (pGetIn->ulSegmentId - 1)) && (pClb->ulSegmId <= (pGetIn->ulSegmentId + 1));
         BOOL fExactExactExistingCLB = ((pTMXTargetClb->usFileId == usGetFile) || (pTMXTargetClb->usFileId == usAlternateGetFile)) &&
         (pTMXTargetClb->ulSegmId >= (pGetIn->ulSegmentId - 1)) && (pTMXTargetClb->ulSegmId <= (pGetIn->ulSegmentId + 1));
         if ( fExactExactNewCLB && !fExactExactExistingCLB )
         {
           // use exact-exact CLB for match
           pTMXTargetClb = pClb;
           usTargetTranslationFlag = usTranslationFlag;
           usContextRanking = usCurContextRanking;
         }
         else if ( (fExactExactNewCLB == fExactExactExistingCLB) && (pClb->lTime > pTMXTargetClb->lTime) )
         {
           // use newer target CLB for match
           pTMXTargetClb = pClb;
           usTargetTranslationFlag = usTranslationFlag;
           usContextRanking = usCurContextRanking;
         }
       } /* endif */
     } /* endif */
   }
   else
   {
     if ( sCurMatch < CONTEXT_MATCH )
     {
     sCurMatch = CONTEXT_MATCH;
     pTMXTargetClb = pClb; // use this target CLB for match
     usTargetTranslationFlag = usTranslationFlag;
     usContextRanking = usCurContextRanking;
     }
     else if ( sCurMatch == CONTEXT_MATCH )
     {
       // we have already a match of this type so check if context ranking
      if ( usCurContextRanking > usContextRanking )
      {
        pTMXTargetClb = pClb; // use newer target CLB for match
        usTargetTranslationFlag = usTranslationFlag;
        usContextRanking = usCurContextRanking;
      }
      // use time info to ensure that latest match is used
     else if ( (usCurContextRanking == usContextRanking) && (pClb->lTime > pTMXTargetClb->lTime) )
     {
       pTMXTargetClb = pClb; // use newer target CLB for match
       usTargetTranslationFlag = usTranslationFlag;
       usContextRanking = usCurContextRanking;
      } /* endif */
    } /* endif */
  } /* endif */
 }
 else if ( fMatchingDocName && (pClb->ulSegmId >= (pGetIn->ulSegmentId - 1)) && (pClb->ulSegmId <= (pGetIn->ulSegmentId + 1)) )
 {
   // same segment from same document available
   sCurMatch = SAME_SEG_AND_DOC_MATCH;
   pTMXTargetClb = pClb; // use this target CLB for match
   usContextRanking = usCurContextRanking;
   usTargetTranslationFlag = usTranslationFlag;
 }
 else if ( fMatchingDocName )
 {
    // segment from same document available
    if ( sCurMatch < SAME_DOC_MATCH )
    {
       sCurMatch = SAME_DOC_MATCH;
       pTMXTargetClb = pClb; // use this target CLB for match
       usTargetTranslationFlag = usTranslationFlag;
       usContextRanking = usCurContextRanking;
     }
     else if ( sCurMatch == SAME_DOC_MATCH )
     {
       // we have already a match of this type so
       // use time info to ensure that latest match is used
       if ( pClb->lTime > pTMXTargetClb->lTime )
       {
         pTMXTargetClb = pClb; // use newer target CLB for match
         usTargetTranslationFlag = usTranslationFlag;
         usContextRanking = usCurContextRanking;
       } /* endif */
     } /* endif */
   }
    else if ( pClb->bMultiple )
    {
       // multiple target segment available
       if ( sCurMatch < MULT_DOC_MATCH )
       {
         // no better match yet
         sCurMatch = MULT_DOC_MATCH;
         pTMXTargetClb = pClb; // use this target CLB for match
         usTargetTranslationFlag = usTranslationFlag;
         usContextRanking = usCurContextRanking;
       } /* endif */
     }
     else if ( usTranslationFlag == TRANSLFLAG_NORMAL )
     {
        // a 'normal' memory match is available
        if ( sCurMatch < NORMAL_MATCH )
        {
           // no better match yet
           sCurMatch = NORMAL_MATCH;
           pTMXTargetClb = pClb; // use this target CLB for match
           usTargetTranslationFlag = usTranslationFlag;
           usContextRanking = usCurContextRanking;
         } /* endif */
     } /* endif */

    // continue with next target CLB
    if ( sCurMatch < SAME_SEG_AND_DOC_MATCH )
    {
      lLeftClbLen -= TARGETCLBLEN(pClb);
      if (lLeftClbLen > 0)
      {
        usTgtNum++;
        pClb = NEXTTARGETCLB(pClb);
      }
    } /* endif */
} /* endwhile */


{
  BOOL fNormalMatch = (usTargetTranslationFlag == TRANSLFLAG_NORMAL) ||
  (usTargetTranslationFlag == TRANSLFLAG_GLOBMEM) ||
  (usTargetTranslationFlag == TRANSLFLAG_GLOBMEMSTAR);
  switch ( sCurMatch )
  {
    case IGNORE_MATCH :
      usMatchLevel = 0;
       break;
  case SAME_SEG_AND_DOC_MATCH :
      usMatchLevel = fNormalMatch ? usEqual+2 : usEqual-1;
      break;
   case SEG_DOC_AND_CONTEXT_MATCH :
       usMatchLevel = fNormalMatch ? usEqual+2 : usEqual-1; // exact-exact match with matching context
       break;
    case DOC_AND_CONTEXT_MATCH :
       if ( usContextRanking == 100 )
       {
         // GQ 2015/05/09: treat 100% context matches as normal exact matches
         // usMatchLevel = fNormalMatch ? usEqual+2 : usEqual-1;
         usMatchLevel = fNormalMatch ? usEqual+1 : usEqual-1;
        }
        else
        {
          usMatchLevel = fNormalMatch ? usEqual+1 : usEqual-1;
        } /* endif */
       break;
  case CONTEXT_MATCH :
    if ( usContextRanking == 100 )
    {
      // GQ 2015/05/09: treat 100% context matches as normal exact context matches
      // usMatchLevel = fNormalMatch ? usEqual+2 : usEqual-1;
      // GQ 2016/10/24: treat 100% context matches as normal exact matches
      usMatchLevel = fNormalMatch ? usEqual : usEqual-1;
    }
    else
    {
      usMatchLevel = fNormalMatch ? usEqual : usEqual-1;
     } /* endif */
     break;
  case SAME_DOC_MATCH :
    usMatchLevel = fNormalMatch ? usEqual+1 : usEqual-1;
    break;
  case MULT_DOC_MATCH :
     usMatchLevel = fNormalMatch ? usEqual+1 : usEqual-1;
     break;
  default :
     usMatchLevel = fNormalMatch ? usEqual : usEqual-1;
     break;
  } /* endswitch */
}
}

Concordance search

Purpose

Returns entries\translations that contain requested segment

Request

POST /%service%/%tm_name%/concordancesearch

Params

Required: searchString - what we are looking for , searchType ["Source"|"Target"|"SourceAndTarget"] - where to look

iNumOfProposal - limit of found proposals - max is 20, if 0 → use default value '5'

Code Block

language	js
title	Response
collapse	true

Request example:
{
    "searchString": "The",
    "searchType": "source",
    ["searchPosition": "",]
    ["numResults": 20,]
    ["msSearchAfterNumResults": 250,]
	["loggingThreshold": 0]
}
Response example:Success:
{
  "ReturnValue": 0,
  "NewSearchPosition": null,
  "results": [
  {
     "source": "For > 100 setups.",
     "target": "Für > 100 Aufstellungen.",
     "segmentNumber": 10906825,
     "id": "",
     "documentName": "none",
     "documentShortName": "NONE",
     "sourceLang": "en-GB",← rfc5646     
     "targetLang": "de-DE",← rfc5646
     "type": "Manual",
     "matchType": "undefined",
     "author": "",
     "timestamp": "20190401T084052Z",
     "matchRate": 0,
     "markupTable": "OTMXML",
     "context": "",
     "additionalInfo": ""
   }
  ],
 "ErrorMsg": ""
}

Success, but with NewSearchPosition - not all TM was checked, use this position to repeat search:
{
  "ReturnValue": 0,
  "NewSearchPosition": "8:1",
  "results": [
  {
     "source": "For > 100 setups.",
     "target": "Für > 100 Aufstellungen.",
     "segmentNumber": 10906825,
     "id": "",
    "documentName": "none",
    "documentShortName": "NONE",
    "sourceLang": "en-GB",
    "targetLang": "de-DE",
    "type": "Manual",
     "matchType": "undefined",
     "author": "",
     "timestamp": "20190401T084052Z",
     "matchRate": 0,
     "markupTable": "OTMXML",
     "context": "",
     "additionalInfo": ""
   }
  ],
 "ErrorMsg": ""
}
SearchPosition / NewSearchPositionFormat: "7:1"
First is segmeng\record number, second is target number
The NextSearchposition is an internal key of the memory for the next position on sequential access. Since it is an internal key, maintained and understood by the underlying memory plug-in (for EqfMemoryPlugin is it the record number and the position in one record),
no assumptions should be made regarding the content. It is just a string that, should be sent back to OpenTM2 on the next request, so that the search starts from there.
So is the implementation in Translate5: The first request to OpenTM2 contains SearchPosition with an empty string, OpenTM2 returns than a string in NewSearchPosition, which is just resent to OpenTM2 in the next request.

Not found:{
"ReturnValue": 0,
"NewSearchPosition": null,
"ErrorMsg": ""
}TM not found:{
"ReturnValue": 133,
"ErrorMsg": "OtmMemoryServiceWorker::concordanceSearch::"
}

...

Page tree

Versions Compared

Old Version 34

New Version 35

Key

Fuzzy search

Concordance search