#807 fix for ncbi_downstream

queries for certain ids, in this case two subgenera, returned themselves and species within those subgenera so the while loop never ended change ncbi_downstream to remove any ids from resulting searches that were in the search themselves also changed to after takig bind rows, then taking unique to remove any duplicate rows
ropensci · Mar 17, 2020 · 8a31336 · 8a31336
1 parent 671a955
commit 8a31336
Show file tree

Hide file tree

Showing 8 changed files with 6,508 additions and 3 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -5,7 +5,7 @@ Description: Interacts with a suite of web 'APIs' for taxonomic tasks,
     species names, getting taxonomic hierarchies, fetching downstream and
     upstream taxonomic names, getting taxonomic synonyms, converting
     scientific to common names and vice versa, and more.
-Version: 0.9.92.95
+Version: 0.9.92.96
 License: MIT + file LICENSE
 URL: https://docs.ropensci.org/taxize (website),
     https://github.com/ropensci/taxize (devel),

diff --git a/R/ncbi_downstream.R b/R/ncbi_downstream.R
@@ -59,6 +59,7 @@ ncbi_downstream <- function(id, downto, intermediate = FALSE, ...) {
     iter <- iter + 1
     tt <- dt2df(lapply(id, function(x) ncbi_children(id = x, ...)[[1]]))
     tt$.id <- NULL
+    tt <- remove_self_ids(tt, id)
     tt <- rename(tt, c('childtaxa_rank' = 'rank'))
     tt <- prune_too_low(tt, downto, ignore_no_rank = TRUE)
 
@@ -86,10 +87,14 @@ ncbi_downstream <- function(id, downto, intermediate = FALSE, ...) {
     if (intermediate) intermed[[iter]] <- intermed[[iter]]
   } # end while loop
 
-  tmp <- dt2df(out, idcol = FALSE)
+  tmp <- unique(dt2df(out, idcol = FALSE))
   if (intermediate) {
     list(target = tmp, intermediate = intermed)
   } else {
     tmp
   }
 }
+
+remove_self_ids <- function(x, id) {
+  x[!as.character(x$childtaxa_id) %in% as.character(id), ]
+}
diff --git a/R/zzz.R b/R/zzz.R
@@ -115,7 +115,7 @@ filt <- function(df, rank, z) {
     df
   } else {
     if (!is.null(z)) {
-      mtch <- grep(sprintf("%s", tolower(z)), tolower(df[,rank]))
+      mtch <- grep(sprintf("^%s$", tolower(z)), tolower(df[,rank]))
       if (length(mtch) != 0) {
         df[mtch, ]
       } else {

diff --git a/tests/fixtures/ncbi_downstream.yml b/tests/fixtures/ncbi_downstream.yml
diff --git a/tests/fixtures/ncbi_downstream_ambiguous_false.yml b/tests/fixtures/ncbi_downstream_ambiguous_false.yml
@@ -0,0 +1,233 @@
+http_interactions:
+- request:
+    method: get
+    uri: https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=taxonomy&ID=590&api_key=<<entrez_api_token>>
+    body:
+      encoding: ''
+      string: ''
+    headers:
+      User-Agent: libcurl/7.64.1 r-curl/4.3 crul/0.9.0
+      Accept-Encoding: gzip, deflate
+      Accept: application/json, text/xml, application/xml, */*
+  response:
+    status:
+      status_code: '200'
+      message: OK
+      explanation: Request fulfilled, document follows
+    headers:
+      status: HTTP/1.1 200 OK
+      date: Tue, 17 Mar 2020 23:06:21 GMT
+      server: Finatra
+      strict-transport-security: max-age=31536000; includeSubDomains; preload
+      content-security-policy: upgrade-insecure-requests
+      x-ratelimit-remaining: '7'
+      ncbi-phid: 322C6F094A3EACC500002B2282BDADFD.1.1.m_3
+      cache-control: private
+      ncbi-sid: 2F119B11C2C5B43F_8242SID
+      content-encoding: gzip
+      x-ratelimit-limit: '10'
+      access-control-allow-origin: '*'
+      content-type: text/xml; charset=UTF-8
+      set-cookie: ncbi_sid=2F119B11C2C5B43F_8242SID; domain=.nih.gov; path=/; expires=Wed,
+        17 Mar 2021 23:06:22 GMT
+      x-ua-compatible: IE=Edge
+      x-xss-protection: 1; mode=block
+      transfer-encoding: chunked
+    body:
+      encoding: UTF-8
+      file: no
+      string: |-
+        <?xml version="1.0" ?>
+        <!DOCTYPE TaxaSet PUBLIC "-//NLM//DTD Taxon, 14th January 2002//EN" "https://www.ncbi.nlm.nih.gov/entrez/query/DTD/taxon.dtd">
+        <TaxaSet><Taxon>
+            <TaxId>590</TaxId>
+            <ScientificName>Salmonella</ScientificName>
+            <OtherNames>
+                <Name>
+                    <ClassCDE>authority</ClassCDE>
+                    <DispName>Salmonella Lignieres 1900</DispName>
+                </Name>
+                <Name>
+                    <ClassCDE>misspelling</ClassCDE>
+                    <DispName>Samonella</DispName>
+                </Name>
+            </OtherNames>
+            <ParentTaxId>543</ParentTaxId>
+            <Rank>genus</Rank>
+            <Division>Bacteria</Division>
+            <GeneticCode>
+                <GCId>11</GCId>
+                <GCName>Bacterial, Archaeal and Plant Plastid</GCName>
+            </GeneticCode>
+            <MitoGeneticCode>
+                <MGCId>0</MGCId>
+                <MGCName>Unspecified</MGCName>
+            </MitoGeneticCode>
+            <Lineage>cellular organisms; Bacteria; Proteobacteria; Gammaproteobacteria; Enterobacterales; Enterobacteriaceae</Lineage>
+            <LineageEx>
+                <Taxon>
+                    <TaxId>131567</TaxId>
+                    <ScientificName>cellular organisms</ScientificName>
+                    <Rank>no rank</Rank>
+                </Taxon>
+                <Taxon>
+                    <TaxId>2</TaxId>
+                    <ScientificName>Bacteria</ScientificName>
+                    <Rank>superkingdom</Rank>
+                </Taxon>
+                <Taxon>
+                    <TaxId>1224</TaxId>
+                    <ScientificName>Proteobacteria</ScientificName>
+                    <Rank>phylum</Rank>
+                </Taxon>
+                <Taxon>
+                    <TaxId>1236</TaxId>
+                    <ScientificName>Gammaproteobacteria</ScientificName>
+                    <Rank>class</Rank>
+                </Taxon>
+                <Taxon>
+                    <TaxId>91347</TaxId>
+                    <ScientificName>Enterobacterales</ScientificName>
+                    <Rank>order</Rank>
+                </Taxon>
+                <Taxon>
+                    <TaxId>543</TaxId>
+                    <ScientificName>Enterobacteriaceae</ScientificName>
+                    <Rank>family</Rank>
+                </Taxon>
+            </LineageEx>
+            <CreateDate>1995/02/27 09:24:00</CreateDate>
+            <UpdateDate>2018/11/23 13:57:51</UpdateDate>
+            <PubDate>1993/04/21 01:00:00</PubDate>
+        </Taxon>
+
+        </TaxaSet>
+  recorded_at: 2020-03-17 23:06:23 GMT
+  recorded_with: vcr/0.5.0.92, webmockr/0.6.0.92
+- request:
+    method: get
+    uri: https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=taxonomy&term=Salmonella%5BNext%20Level%5D%20AND%20Enterobacteriaceae%5Bsubtree%5D&RetMax=1000&RetStart=0&api_key=<<entrez_api_token>>
+    body:
+      encoding: ''
+      string: ''
+    headers:
+      Accept-Encoding: gzip, deflate
+      Accept: application/json, text/xml, application/xml, */*
+      User-Agent: r-curl/4.3 crul/0.9.0 rOpenSci(taxize/0.9.92.96)
+      X-USER-AGENT: r-curl/4.3 crul/0.9.0 rOpenSci(taxize/0.9.92.96)
+  response:
+    status:
+      status_code: '200'
+      message: OK
+      explanation: Request fulfilled, document follows
+    headers:
+      status: HTTP/1.1 200 OK
+      date: Tue, 17 Mar 2020 23:06:22 GMT
+      server: Finatra
+      strict-transport-security: max-age=31536000; includeSubDomains; preload
+      content-security-policy: upgrade-insecure-requests
+      x-ratelimit-remaining: '7'
+      ncbi-phid: 322C6F094A3EACC5000057228329FDCD.1.1.m_1
+      cache-control: private
+      ncbi-sid: D70139B1B6121A77_10D1SID
+      content-encoding: gzip
+      x-ratelimit-limit: '10'
+      access-control-allow-origin: '*'
+      content-type: text/xml; charset=UTF-8
+      set-cookie: ncbi_sid=D70139B1B6121A77_10D1SID; domain=.nih.gov; path=/; expires=Wed,
+        17 Mar 2021 23:06:22 GMT
+      x-ua-compatible: IE=Edge
+      x-xss-protection: 1; mode=block
+      transfer-encoding: chunked
+    body:
+      encoding: UTF-8
+      file: no
+      string: |
+        <?xml version="1.0" encoding="UTF-8" ?>
+        <!DOCTYPE eSearchResult PUBLIC "-//NLM//DTD esearch 20060628//EN" "https://eutils.ncbi.nlm.nih.gov/eutils/dtd/20060628/esearch.dtd">
+        <eSearchResult><Count>5</Count><RetMax>5</RetMax><RetStart>0</RetStart><IdList>
+        <Id>2614656</Id>
+        <Id>2588448</Id>
+        <Id>263770</Id>
+        <Id>54736</Id>
+        <Id>28901</Id>
+        </IdList><TranslationSet/><TranslationStack>   <TermSet>    <Term>Salmonella[Next Level]</Term>    <Field>Next Level</Field>    <Count>5</Count>    <Explode>N</Explode>   </TermSet>   <TermSet>    <Term>Enterobacteriaceae[subtree]</Term>    <Field>subtree</Field>    <Count>20383</Count>    <Explode>N</Explode>   </TermSet>   <OP>AND</OP>  </TranslationStack><QueryTranslation>Salmonella[Next Level] AND Enterobacteriaceae[subtree]</QueryTranslation></eSearchResult>
+  recorded_at: 2020-03-17 23:06:23 GMT
+  recorded_with: vcr/0.5.0.92, webmockr/0.6.0.92
+- request:
+    method: get
+    uri: https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi?db=taxonomy&id=2614656%2B2588448%2B263770%2B54736%2B28901&api_key=<<entrez_api_token>>
+    body:
+      encoding: ''
+      string: ''
+    headers:
+      Accept-Encoding: gzip, deflate
+      Accept: application/json, text/xml, application/xml, */*
+      User-Agent: r-curl/4.3 crul/0.9.0 rOpenSci(taxize/0.9.92.96)
+      X-USER-AGENT: r-curl/4.3 crul/0.9.0 rOpenSci(taxize/0.9.92.96)
+  response:
+    status:
+      status_code: '200'
+      message: OK
+      explanation: Request fulfilled, document follows
+    headers:
+      status: HTTP/1.1 200 OK
+      date: Tue, 17 Mar 2020 23:06:21 GMT
+      server: Finatra
+      strict-transport-security: max-age=31536000; includeSubDomains; preload
+      content-security-policy: upgrade-insecure-requests
+      x-ratelimit-remaining: '7'
+      ncbi-phid: 322C6F094A3EACC50000462283D1BCF7.1.1.m_1
+      cache-control: private
+      ncbi-sid: 635BE0A98532F318_CF43SID
+      content-encoding: gzip
+      x-ratelimit-limit: '10'
+      access-control-allow-origin: '*'
+      content-type: text/xml; charset=UTF-8
+      set-cookie: ncbi_sid=635BE0A98532F318_CF43SID; domain=.nih.gov; path=/; expires=Wed,
+        17 Mar 2021 23:06:22 GMT
+      x-ua-compatible: IE=Edge
+      x-xss-protection: 1; mode=block
+      transfer-encoding: chunked
+    body:
+      encoding: UTF-8
+      file: no
+      string: "<?xml version=\"1.0\" encoding=\"UTF-8\" ?>\n<!DOCTYPE eSummaryResult
+        PUBLIC \"-//NLM//DTD esummary v1 20041029//EN\" \"https://eutils.ncbi.nlm.nih.gov/eutils/dtd/20041029/esummary-v1.dtd\">\n<eSummaryResult>\n<DocSum>\n\t<Id>2614656</Id>\n\t<Item
+        Name=\"Status\" Type=\"String\">active</Item>\n\t<Item Name=\"Rank\" Type=\"String\"></Item>\n\t<Item
+        Name=\"Division\" Type=\"String\">enterobacteria</Item>\n\t<Item Name=\"ScientificName\"
+        Type=\"String\">unclassified Salmonella</Item>\n\t<Item Name=\"CommonName\"
+        Type=\"String\"></Item>\n\t<Item Name=\"TaxId\" Type=\"Integer\">2614656</Item>\n\t<Item
+        Name=\"AkaTaxId\" Type=\"Integer\">0</Item>\n\t<Item Name=\"Genus\" Type=\"String\"></Item>\n\t<Item
+        Name=\"Species\" Type=\"String\"></Item>\n\t<Item Name=\"Subsp\" Type=\"String\"></Item>\n\t<Item
+        Name=\"ModificationDate\" Type=\"Date\">2019/09/22 00:00</Item>\n</DocSum>\n\n<DocSum>\n\t<Id>2588448</Id>\n\t<Item
+        Name=\"Status\" Type=\"String\">active</Item>\n\t<Item Name=\"Rank\" Type=\"String\"></Item>\n\t<Item
+        Name=\"Division\" Type=\"String\">enterobacteria</Item>\n\t<Item Name=\"ScientificName\"
+        Type=\"String\">Salmonella sp. SH11G0791</Item>\n\t<Item Name=\"CommonName\"
+        Type=\"String\"></Item>\n\t<Item Name=\"TaxId\" Type=\"Integer\">2588448</Item>\n\t<Item
+        Name=\"AkaTaxId\" Type=\"Integer\">0</Item>\n\t<Item Name=\"Genus\" Type=\"String\"></Item>\n\t<Item
+        Name=\"Species\" Type=\"String\"></Item>\n\t<Item Name=\"Subsp\" Type=\"String\"></Item>\n\t<Item
+        Name=\"ModificationDate\" Type=\"Date\">2019/06/13 00:00</Item>\n</DocSum>\n\n<DocSum>\n\t<Id>263770</Id>\n\t<Item
+        Name=\"Status\" Type=\"String\">active</Item>\n\t<Item Name=\"Rank\" Type=\"String\"></Item>\n\t<Item
+        Name=\"Division\" Type=\"String\">enterobacteria</Item>\n\t<Item Name=\"ScientificName\"
+        Type=\"String\">environmental samples</Item>\n\t<Item Name=\"CommonName\"
+        Type=\"String\"></Item>\n\t<Item Name=\"TaxId\" Type=\"Integer\">263770</Item>\n\t<Item
+        Name=\"AkaTaxId\" Type=\"Integer\">0</Item>\n\t<Item Name=\"Genus\" Type=\"String\"></Item>\n\t<Item
+        Name=\"Species\" Type=\"String\"></Item>\n\t<Item Name=\"Subsp\" Type=\"String\"></Item>\n\t<Item
+        Name=\"ModificationDate\" Type=\"Date\">2018/10/18 00:00</Item>\n</DocSum>\n\n<DocSum>\n\t<Id>54736</Id>\n\t<Item
+        Name=\"Status\" Type=\"String\">active</Item>\n\t<Item Name=\"Rank\" Type=\"String\">species</Item>\n\t<Item
+        Name=\"Division\" Type=\"String\">enterobacteria</Item>\n\t<Item Name=\"ScientificName\"
+        Type=\"String\">Salmonella bongori</Item>\n\t<Item Name=\"CommonName\" Type=\"String\"></Item>\n\t<Item
+        Name=\"TaxId\" Type=\"Integer\">54736</Item>\n\t<Item Name=\"AkaTaxId\" Type=\"Integer\">0</Item>\n\t<Item
+        Name=\"Genus\" Type=\"String\">Salmonella</Item>\n\t<Item Name=\"Species\"
+        Type=\"String\">bongori</Item>\n\t<Item Name=\"Subsp\" Type=\"String\"></Item>\n\t<Item
+        Name=\"ModificationDate\" Type=\"Date\">2018/10/31 00:00</Item>\n</DocSum>\n\n<DocSum>\n\t<Id>28901</Id>\n\t<Item
+        Name=\"Status\" Type=\"String\">active</Item>\n\t<Item Name=\"Rank\" Type=\"String\">species</Item>\n\t<Item
+        Name=\"Division\" Type=\"String\">enterobacteria</Item>\n\t<Item Name=\"ScientificName\"
+        Type=\"String\">Salmonella enterica</Item>\n\t<Item Name=\"CommonName\" Type=\"String\"></Item>\n\t<Item
+        Name=\"TaxId\" Type=\"Integer\">28901</Item>\n\t<Item Name=\"AkaTaxId\" Type=\"Integer\">0</Item>\n\t<Item
+        Name=\"Genus\" Type=\"String\">Salmonella</Item>\n\t<Item Name=\"Species\"
+        Type=\"String\">enterica</Item>\n\t<Item Name=\"Subsp\" Type=\"String\"></Item>\n\t<Item
+        Name=\"ModificationDate\" Type=\"Date\">2019/10/07 00:00</Item>\n</DocSum>\n\n</eSummaryResult>\n"
+  recorded_at: 2020-03-17 23:06:23 GMT
+  recorded_with: vcr/0.5.0.92, webmockr/0.6.0.92