NCBI C Toolkit Cross Reference

   NCBI NETWORK SERVICES FOR ENTREZ QUERIES AND SEQUENCE FETCHING
   
   NCBI has new network services for Entrez (term lists, Boolean queries,
   document summaries, neighbors and links) and PubMed and Sequence record
   fetching.  These are all CGI-based, were written by the group that maintains
   our web services, and have a lot of advantages over our older network
   services.
   
   The code is all in the ncbi/access folder, and is compiled into the ncbiobj
  library, along with the object loaders and api functions.  This library is
  always linked in with our applications, and does not depend upon netcli or
  netentr libraries.  The network connection functions are in the ncbi and
  ncbiconn libraries, also always linked in.  The header files are ent2api.h
  for Entrez2 services and pmfapi.h for PubMed and sequence fetching.
  
  These functions are now accessed as named services, so the underlying URL is
  not present in the client code.  This allows us to redirect requests between
  multiple servers for load balancing, and to change minor URL parameters as
  needed without breaking the client.  The only parameters the client sends are
  essential ones (e.g., gi number).  These services will thus be stable and
  supported over time, regardless of what we do behind the scenes.
  
  Another advantage is that the services can be called either synchronously or
  asynchronously.  Synchronous queries wait for the reply before returning
  control back to your program, and are easier to code.  For example:
  
    PubmedEntryPtr pep = PubMedSynchronousQuery (pmid);
  
    SeqEntryPtr sep = PubSeqSynchronousQuery (gi, 0, 0);
  
  These do not automatically try to reconnect if the network request failed,
  and the client can decide whether to put these calls in a small retry loop.
  
  Asynchronous queries are slighly more complicated to code, but allow better
  responsiveness, without the need for multi-threading in interactive programs.
  Asynchronous calls send the request to the server, add a block of data with
  the connection and your callback function to a queue, and immediately return
  control to your program.  You are responsible for calling a queue checking
  function every so often, typically on a timer.  When the results are ready,
  the queue checker calls the callback you specified.  Your callback reads the
  data, does whatever you want with it, and returns to the queue checker, which
  cleans up the connection before returning to the timer event loop.
  
  Some NCBI toolkit library functions require the ability to fetch sequences
  from a registered service.  For this, you can call
  
    PubSeqFetchEnable ();
  
  to enable access and
  
    PubSeqFetchDisable ();
  
  to disable access.  The asn2gb -r flag (for remote access) works this way.
  
  The demo/entrez2 application uses desktop/e2trmlst.c and desktop/e2docsum.c
  to access the new servers.
  
  Some examples of how to use the new functions are provided below.
  
  
  /* standard startup */
  
  #include <sqnutils.h>
  #include <objall.h>
  #include <objsub.h>
  #include <objfdef.h>
  
  static void StandardStartup (void)
  
  {
    ErrSetFatalLevel (SEV_MAX);
    ErrClearOptFlags (EO_SHOW_USERSTR);
    UseLocalAsnloadDataAndErrMsg ();
    ErrPathReset ();
  
    AllObjLoad ();
    SubmitAsnLoad ();
    FeatDefSetLoad ();
    SeqCodeSetLoad ();
    GeneticCodeTableLoad ();
  }
  
  /* enabling automatic fetch of components from SeqFetch service */
  
  #include <pmfapi.h>
  
  static void OnStartup (void)
  
  {
    PubSeqFetchEnable ();
  }
  
  static void OnShutdown (void)
  
  {
    PubSeqFetchDisable ();
  }
  
  /* example of fetching PubMed record */
 
 #include <pmfapi.h>
 #include <tomedlin.h>
 
 static void SavePubMedRecord (Int4 pmid, FILE *fp)
 
 {
   PubmedEntryPtr  pep;
 
   pep = PubMedSynchronousQuery (pmid);
   if (pep == NULL) return;
 
   MedlineEntryToDataFile ((MedlineEntryPtr) pep->medent, fp);
   PubmedEntryFree (pep);
 }
 
 /* example of fetching sequence record */
 
 #include <pmfapi.h>
 #include <asn2gnbk.h>
 
 static void SaveSeqRecord (Int4 gi, FILE *fp)
 
 {
   SeqEntryPtr  sep;
 
   sep = PubSeqSynchronousQuery (gi, 0, 0);
   if (sep == NULL) return;
 
   SeqEntryToGnbk (sep, NULL, GENBANK_FMT, RELEASE_MODE, NORMAL_STYLE,
                   0, 0, 0, NULL, fp);
   SeqEntryFree (sep);
 }
 
 /* example of Entrez2 Boolean query */
 
 #include <ent2api.h>
 
 static void DoBooleanRequest (FILE *fp)
 
 {
   Entrez2BooleanReplyPtr  e2br;
   Entrez2IdListPtr        e2id;
   Entrez2RequestPtr       e2rq;
   Entrez2ReplyPtr         e2ry;
   Int4                    i;
   Int4Ptr                 uids;
 
   e2rq = EntrezCreateBooleanRequest (TRUE, FALSE, "Nucleotide", NULL,
                                      0, 0, NULL, 0, 0);
   if (e2rq == NULL) return;
 
   EntrezAddToBooleanRequest (e2rq, NULL, 0, "ORGN", "Saccharomyces cerevisiae",
                              NULL, 0, 0, NULL, NULL, TRUE, TRUE);
   EntrezAddToBooleanRequest (e2rq, NULL, ENTREZ_OP_AND, NULL, NULL,
                              NULL, 0, 0, NULL, NULL, TRUE, TRUE);
   EntrezAddToBooleanRequest (e2rq, NULL, 0, "PROP", "biomol mrna",
                              NULL, 0, 0, NULL, NULL, TRUE, TRUE);
 
   e2ry = EntrezSynchronousQuery (e2rq);
   e2rq = Entrez2RequestFree (e2rq);
   if (e2ry == NULL) return;
 
   e2br = EntrezExtractBooleanReply (e2ry);
   if (e2br == NULL) return;
 
   if (e2br->count > 0) {
     e2id = e2br->uids;
 
     if (e2id != NULL && e2id->num > 0 && e2id->uids != NULL) {
       fprintf (fp, "count=%ld\n", (long) e2id->num);
 
       uids = (Int4Ptr) BSMerge (e2id->uids, NULL);
       if (uids != NULL) {
         for (i = 0; i < e2id->num; i++) {
           fprintf (fp, "pmid=%ld\n", (long) uids [i]);
         }
         MemFree (uids);
       }
     }
   }
 
   Entrez2BooleanReplyFree (e2br);
 }
 
 /* example of fetching Entrez2 document summary */
 
 #include <ent2api.h>
 
 static void DoDocsumRequest (Int4 pmid, FILE *fp)
 
 {
   Entrez2DocsumDataPtr  e2ddp;
   Entrez2DocsumListPtr  e2dlp;
   Entrez2DocsumPtr      e2dp;
   Entrez2RequestPtr     e2rq;
   Entrez2ReplyPtr       e2ry;
 
   e2rq = EntrezCreateDocSumRequest ("PubMed", pmid, 0, NULL, NULL);
   if (e2rq == NULL) return;
 
   e2ry = EntrezSynchronousQuery (e2rq);
   e2rq = Entrez2RequestFree (e2rq);
   if (e2ry == NULL) return;
 
   e2dlp = EntrezExtractDocsumReply (e2ry);
   if (e2dlp == NULL) return;
 
   for (e2dp = e2dlp->list; e2dp != NULL; e2dp = e2dp->next) {
     for (e2ddp = e2dp->docsum_data; e2ddp != NULL; e2ddp = e2ddp->next) {
       if (StringHasNoText (e2ddp->field_name)) continue;
       if (StringHasNoText (e2ddp->field_value)) continue;
       fprintf (fp, "%s - %s\n", e2ddp->field_name, e2ddp->field_value);
     }
   }
 
   Entrez2DocsumListFree (e2dlp);
 }