@teselagen/bio-parsers 0.3.7 → 0.3.9

package/src/ab1ToJson.js

@@ -10,7 +10,7 @@ async function ab1ToJson(fileObj, options = {}) {
   returnVal.parsedSequence = {
     ...returnVal.parsedSequence,
     sequence: chromatogramData.baseCalls.join(""),
-    chromatogramData,
+    chromatogramData
   };
   return [returnVal];
 }
@@ -22,7 +22,6 @@ function abConverter(inputArrayBuffer) {
   const numElements = inputArrayBuffer.getInt32(18);
   const lastEntry = dirLocation + numElements * 28;
 
-
   this.getNumber = (inOffset, numEntries) => {
     const retArray = [];
     for (let counter = 0; counter < numEntries; counter += 1) {
@@ -49,8 +48,7 @@ function abConverter(inputArrayBuffer) {
     return retArray;
   };
 
-
-  this.getTagName = (inOffset) => {
+  this.getTagName = inOffset => {
     let name = "";
     for (let loopOffset = inOffset; loopOffset < inOffset + 4; loopOffset++) {
       name += String.fromCharCode(inputArrayBuffer.getInt8(loopOffset));
@@ -58,7 +56,7 @@ function abConverter(inputArrayBuffer) {
     return name;
   };
 
-  this.getDataTag = function(inTag) {
+  this.getDataTag = function (inTag) {
     let output;
     let curElem = dirLocation;
     do {
@@ -75,7 +73,7 @@ function abConverter(inputArrayBuffer) {
     return output;
   };
 
-  this.getTraceData = function() {
+  this.getTraceData = function () {
     const traceData = {};
     traceData.aTrace = this.getDataTag(tagDict.colorDataA);
     traceData.tTrace = this.getDataTag(tagDict.colorDataT);
@@ -84,10 +82,10 @@ function abConverter(inputArrayBuffer) {
     traceData.basePos = this.getDataTag(tagDict.peakLocations);
     traceData.baseCalls = this.getDataTag(tagDict.baseCalls2);
     traceData.qualNums = this.getDataTag(tagDict.qualNums);
-    if (traceData.qualNums ) { 
+    if (traceData.qualNums) {
       //tnr if we're only getting 1's and 0's as qualNums, that means that there weren't actual qual nums attached to the file
-      if (!traceData.qualNums.filter(q => (q!==1 && q!==0)).length)  {
-        delete traceData.qualNums
+      if (!traceData.qualNums.filter(q => q !== 1 && q !== 0).length) {
+        delete traceData.qualNums;
       }
     }
     return convertBasePosTraceToPerBpTrace(traceData);
@@ -116,11 +114,10 @@ const tagDict = {
   colorDataA: { tagName: "DATA", tagNum: 10, typeToReturn: "getShort" },
   colorDataT: { tagName: "DATA", tagNum: 11, typeToReturn: "getShort" },
   colorDataG: { tagName: "DATA", tagNum: 9, typeToReturn: "getShort" },
-  colorDataC: { tagName: "DATA", tagNum: 12, typeToReturn: "getShort" },
+  colorDataC: { tagName: "DATA", tagNum: 12, typeToReturn: "getShort" }
 };
 
-
-const correctionAmount = 3
+const correctionAmount = 3;
 // tnr: this function takes in chromData which has 4 traces and a basePos (which describes where in the trace the base call lands)
 // It "normalizes" that data into a baseTraces array so that each base has its own set of that data (having a per-base trace makes insertion/deletion/copy/paste actions all easier)
 function convertBasePosTraceToPerBpTrace(chromData) {
@@ -152,15 +149,15 @@ function convertBasePosTraceToPerBpTrace(chromData) {
       "gTrace",
       "cTrace"
       // eslint-disable-next-line no-loop-func
-    ].forEach((type) => {
+    ].forEach(type => {
       const traceForType = tracesForType[type];
       const traceData = chromData[type];
       for (let j = startPos; j < endPos + correctionAmount; j++) {
         traceForType.push(traceData[j] || 0);
       }
     });
-    if (i !== basePos.length-1) {
-      startPos = endPos+correctionAmount;
+    if (i !== basePos.length - 1) {
+      startPos = endPos + correctionAmount;
       nextBasePos = basePos[i + 2];
       setEndPos();
     }
@@ -172,6 +169,4 @@ function convertBasePosTraceToPerBpTrace(chromData) {
   };
 }
 
-export {
-  convertBasePosTraceToPerBpTrace
-}
+export { convertBasePosTraceToPerBpTrace };

package/src/anyToJson.js

@@ -71,7 +71,7 @@ async function anyToJson(fileContentStringOrFileObj, options) {
   }
   // console.log(`fileContentString.includes("seq:seq"):`,fileContentString.includes("seq:seq"))
   // console.log(`fileContentString.includes("jbei")):`,fileContentString.includes("jbei"))
-  if (/^(fasta|fas|fa|fna|ffn)$/.test(ext)) {
+  if (/^(fasta|fas|fa|fna|ffn|faa)$/.test(ext)) {
     // FASTA
     return fastaToJson(fileContentString, options);
   } else if (/^(gb|gbk)$/.test(ext)) {
@@ -132,12 +132,12 @@ async function anyToJson(fileContentStringOrFileObj, options) {
 
     //try to guess the file type based on the first non-whitespace char in the filestring
     if (firstChar === ">") {
-      parsersToTry = parsersToTry.sort((a) => {
+      parsersToTry = parsersToTry.sort(a => {
         if (a.name === "Fasta Parser") return -1;
         return 1;
       });
     } else if (firstChar === "L") {
-      parsersToTry = parsersToTry.sort((a) => {
+      parsersToTry = parsersToTry.sort(a => {
         if (a.name === "Genbank Parser") return -1;
         return 1;
       });
@@ -188,10 +188,10 @@ function getUtf8StringFromFile(file, { emulateBrowser } = {}) {
   const reader = new window.FileReader();
   reader.readAsText(file, "UTF-8");
   return new Promise((resolve, reject) => {
-    reader.onload = (evt) => {
+    reader.onload = evt => {
       resolve(evt.target.result);
     };
-    reader.onerror = (err) => {
+    reader.onerror = err => {
       console.error("err:", err);
       reject(err);
     };
@@ -212,12 +212,12 @@ function getUint8ArrayFromFile(file, { emulateBrowser } = {}) {
   reader.readAsArrayBuffer(file);
 
   return new Promise((resolve, reject) => {
-    reader.onload = (evt) => {
+    reader.onload = evt => {
       const arrayBuffer = evt.target.result;
       const bytes = new Uint8Array(arrayBuffer);
       resolve(bytes);
     };
-    reader.onerror = (err) => {
+    reader.onerror = err => {
       console.error("err:", err);
       reject(err);
     };

package/src/fastaToJson.js

@@ -1,4 +1,5 @@
 import createInitialSequence from "./utils/createInitialSequence";
+import extractFileExtension from "./utils/extractFileExtension";
 import splitStringIntoLines from "./utils/splitStringIntoLines.js";
 import validateSequenceArray from "./utils/validateSequenceArray";
 
@@ -9,7 +10,12 @@ import validateSequenceArray from "./utils/validateSequenceArray";
  * @author Joshua P Nixon
  */
 
-function fastaToJson(fileString, options) {
+function fastaToJson(fileString, options = {}) {
+  const ext = extractFileExtension(options.fileName);
+  if (/^(faa)$/.test(ext)) {
+    options.isProtein = true;
+  }
+
   let resultArray = [];
   let result = null;
   try {
@@ -28,8 +34,8 @@ function fastaToJson(fileString, options) {
     resultArray = [
       {
         success: false,
-        messages: ["Import Error: Invalid File"],
-      },
+        messages: ["Import Error: Invalid File"]
+      }
     ];
   }
   return validateSequenceArray(resultArray, options);
@@ -71,10 +77,9 @@ function fastaToJson(fileString, options) {
   }
 
   function parseTitle(line) {
-
-    if (options && 'parseName' in options && !options.parseName){
-      result.parsedSequence.name = line.slice(1)
-      return
+    if (options && "parseName" in options && !options.parseName) {
+      result.parsedSequence.name = line.slice(1);
+      return;
     }
 
     const pipeIndex = line.indexOf("|");

package/src/genbankToJson.js

@@ -66,18 +66,20 @@ function genbankToJson(string, options = {}) {
       const isKey = isKeyword(line);
 
       //only set a new LINETYPE in the case that we've encountered a key that warrants it.
-      if (key === "LOCUS") {
-        LINETYPE = key;
-      } else if (key === "REFERENCE") {
-        LINETYPE = key;
-      } else if (key === "FEATURES") {
-        LINETYPE = key;
-      } else if (key === "ORIGIN") {
-        LINETYPE = key;
-      } else if (key === "//") {
-        LINETYPE = key;
-      } else if (isKey === true) {
-        LINETYPE = key;
+      if (!isKeyRunon) {
+        if (key === "LOCUS") {
+          LINETYPE = key;
+        } else if (key === "REFERENCE") {
+          LINETYPE = key;
+        } else if (key === "FEATURES") {
+          LINETYPE = key;
+        } else if (key === "ORIGIN") {
+          LINETYPE = key;
+        } else if (key === "//") {
+          LINETYPE = key;
+        } else if (isKey === true) {
+          LINETYPE = key;
+        }
       }
 
       // IGNORE LINES: DO NOT EVEN PROCESS
@@ -237,10 +239,10 @@ function genbankToJson(string, options = {}) {
   // default sequence json has primers at the top level separate from features, e.g. parsedSequence: { primers: [ {}, {} ], features: [ {}, {} ] }
   // if options.primersAsFeatures is set to true, primers are included in features with type set to primer
 
-  results.forEach((result) => {
+  results.forEach(result => {
     if (result.success) {
       const sequence = result.parsedSequence;
-      sequence.features.forEach((feat) => {
+      sequence.features.forEach(feat => {
         if (feat.type === "primer") {
           feat.type = "primer_bind";
         }
@@ -248,10 +250,10 @@ function genbankToJson(string, options = {}) {
 
       if (!options.primersAsFeatures) {
         sequence.primers = sequence.features.filter(
-          (feat) => feat.type === "primer_bind"
+          feat => feat.type === "primer_bind"
         );
         sequence.features = sequence.features.filter(
-          (feat) => feat.type !== "primer_bind"
+          feat => feat.type !== "primer_bind"
         );
       }
     }
@@ -298,7 +300,6 @@ function genbankToJson(string, options = {}) {
 
   function parseLocus(line) {
     result = createInitialSequence(options);
-    let locusName;
     let circular;
 
     let gbDivision;
@@ -312,7 +313,7 @@ function genbankToJson(string, options = {}) {
       // TODO
       addMessage("Import Warning: Locus line contains no values: " + line);
     }
-    locusName = lineArr[1];
+    const locusName = lineArr[1];
 
     // Linear vs Circular?
     for (let i = 1; i < lineArr.length; i++) {
@@ -525,13 +526,13 @@ function genbankToJson(string, options = {}) {
   }
 
   function parseFeatureNote(line) {
-    let newLine, lineArr;
+    let newLine;
 
     // only trim file formatting spaces (i.e. the left ones)
     // spaces on the right are necessary (e.g. spacing between words, etc.)
     newLine = line.trimLeft();
     newLine = newLine.replace(/^\/|"$/g, "");
-    lineArr = newLine.split(/="|=/);
+    const lineArr = newLine.split(/="|=/);
 
     let val = lineArr.slice(1).join("=");
 

package/src/geneiousXmlToJson.js

@@ -40,7 +40,7 @@ async function geneiousXmlToJson(string, options) {
         messages: ["Error: XML is not valid geneious format"]
       });
     }
-    forEach(geneiousJsonMatches, (geneiousJson) => {
+    forEach(geneiousJsonMatches, geneiousJson => {
       const response = {
         parsedSequence: null,
         messages: [],
@@ -58,10 +58,7 @@ async function geneiousXmlToJson(string, options) {
         });
       }
     });
-    const toRet = filter(
-      resultArray,
-      (r) => r?.parsedSequence?.sequence?.length
-    );
+    const toRet = filter(resultArray, r => r?.parsedSequence?.sequence?.length);
     if (toRet.length) return toRet;
     return onFileParsed(resultArray);
   } catch (e) {
@@ -105,7 +102,7 @@ function parseGeneiousJson(geneiousJson) {
           searchWholeObjByNameSimple("maximumIndex", lastInterval) - 1;
         let locations;
         if (intervals.length > 1) {
-          locations = intervals.map((i) => {
+          locations = intervals.map(i => {
             const start = searchWholeObjByNameSimple("minimumIndex", i) - 1;
             const end = searchWholeObjByNameSimple("maximumIndex", i) - 1;
             return {

package/src/gffToJson.js

@@ -6,7 +6,7 @@ function gffToJson(string) {
   const results = [];
   const sequences = [];
   const features = {};
-  arrayOfThings.forEach((featureOrSeq) => {
+  arrayOfThings.forEach(featureOrSeq => {
     if (featureOrSeq.sequence) {
       sequences.push(featureOrSeq);
     } else {
@@ -19,11 +19,11 @@ function gffToJson(string) {
         start: feature.start,
         end: feature.end,
         strand: feature.strand === "+" ? 1 : -1,
-        type: feature.type,
+        type: feature.type
       });
     }
   });
-  sequences.forEach((sequence) => {
+  sequences.forEach(sequence => {
     const sequenceId = sequence.id;
     const result = {
       messages: [],
@@ -32,8 +32,8 @@ function gffToJson(string) {
         name: sequenceId,
         sequence: sequence.sequence,
         circular: false,
-        features: features[sequence.id],
-      },
+        features: features[sequence.id]
+      }
     };
     results.push(result);
   });

package/src/jbeiXmlToJson.js

@@ -25,14 +25,14 @@ async function jbeiXmlToJson(string, options) {
     if (!jbeiSeq) {
       return onFileParsed({
         success: false,
-        messages: ["Error: XML is not valid jbei format"],
+        messages: ["Error: XML is not valid jbei format"]
       });
     }
 
     const response = {
       parsedSequence: null,
       messages: [],
-      success: true,
+      success: true
     };
     try {
       response.parsedSequence = parseJbeiXml(jbeiSeq, options);
@@ -42,21 +42,18 @@ async function jbeiXmlToJson(string, options) {
       console.error("error.stack: ", e.stack);
       resultArray.push({
         success: false,
-        messages: ["Error while parsing JBEI format"],
+        messages: ["Error while parsing JBEI format"]
       });
     }
 
-    const toRet = filter(
-      resultArray,
-      (r) => r?.parsedSequence?.sequence?.length
-    );
+    const toRet = filter(resultArray, r => r?.parsedSequence?.sequence?.length);
     if (toRet.length) return toRet;
     return onFileParsed(resultArray);
   } catch (e) {
     console.error(`e:`, e);
     return onFileParsed({
       success: false,
-      messages: ["Error parsing jbei to JSON"],
+      messages: ["Error parsing jbei to JSON"]
     });
   }
 }
@@ -65,7 +62,7 @@ function parseJbeiXml(jbeiJson) {
     "seq:sequence": sequence,
     "seq:name": name,
     "seq:circular": circular,
-    "seq:features": { "seq:feature": features },
+    "seq:features": { "seq:feature": features }
   } = jbeiJson;
   return {
     sequence,
@@ -76,7 +73,7 @@ function parseJbeiXml(jbeiJson) {
         "seq:complement": complement,
         "seq:label": label,
         "seq:type": type,
-        "seq:location": jbeiLocations,
+        "seq:location": jbeiLocations
       }) => {
         let start, end;
         const locs = Array.isArray(jbeiLocations)
@@ -88,7 +85,7 @@ function parseJbeiXml(jbeiJson) {
             if (i === locs.length - 1) end = normEnd - 1;
             return {
               start: gbStart - 1,
-              end: normEnd - 1,
+              end: normEnd - 1
             };
           }
         );
@@ -99,10 +96,10 @@ function parseJbeiXml(jbeiJson) {
           locations: locations.length > 1 ? locations : undefined,
           name: label,
           type,
-          strand: complement ? -1 : 1,
+          strand: complement ? -1 : 1
         };
       }
-    ),
+    )
   };
 }
 

package/src/jsonToBed.js

@@ -15,7 +15,7 @@ function jsonToBed(jsonSequence, options = {}) {
   let outString = "";
   outString += `track name="${sequenceNameToUse}" description="${name} Annotations" itemRgb="On"\n`;
 
-  features.forEach(function(feat) {
+  features.forEach(function (feat) {
     const { start, end, name, type, forward, strand } = feat;
     const label = name ? name : type;
     let orientation;
@@ -30,8 +30,9 @@ function jsonToBed(jsonSequence, options = {}) {
     const color = type === "CDS" ? "230,88,0" : "";
     // chromStart is 0-based, chromEnd of the BED file format is not included in the feature
     // when there is no thick part, thickStart and thickEnd are usually set to the chromStart position
-    outString += `${sequenceNameToUse}\t${start}\t${end +
-      1}\t${label}\t\t${orientation}\t\t\t${color}\n`;
+    outString += `${sequenceNameToUse}\t${start}\t${
+      end + 1
+    }\t${label}\t\t${orientation}\t\t\t${color}\n`;
   });
   return outString;
 }

package/src/jsonToFasta.js

@@ -11,7 +11,7 @@ export default function jsonToFasta(jsonSequence, options) {
     sequence,
     isProtein,
     proteinSize,
-    proteinSequence,
+    proteinSequence
   } = cleanedData;
 
   options = options || {};
@@ -25,7 +25,9 @@ export default function jsonToFasta(jsonSequence, options) {
   let fastaString = "";
   fastaString += `>${name || "Untitled Sequence"}|`;
   fastaString += "|" + sizeToUse;
-  fastaString += description ? "|" + mangleOrStripUrls(description, options) : "";
+  fastaString += description
+    ? "|" + mangleOrStripUrls(description, options)
+    : "";
   fastaString += "|" + (circular ? "circular" : "linear");
   fastaString += "\n";
   fastaString += (seqToUse.match(/.{1,80}/g) || []).join("\n");

package/src/jsonToGenbank.js

@@ -49,7 +49,7 @@ const StringUtil = {
     let str = line;
     while (str.length < length) str = str + padString;
     return str;
-  },
+  }
 };
 
 const DIGEST_PART_EXPORT_FIELD_MAP = {
@@ -64,7 +64,7 @@ const DIGEST_PART_EXPORT_FIELD_MAP = {
   "re3Prime.recognitionRegex": "re3PrimePattern",
   re3PrimeOverhang: "re3PrimeOverhang",
   re3PrimeOverhangStrand: "re3PrimeOverhangStrand",
-  re3PrimeRecognitionTypeCode: "re3PrimeRecognitionTypeCode",
+  re3PrimeRecognitionTypeCode: "re3PrimeRecognitionTypeCode"
 };
 
 function cutUpArray(val, start, end) {
@@ -129,7 +129,7 @@ export default function (_serSeq, options) {
 
     serSeq.features = map(serSeq.features).concat(
       flatMap(pragmasAndTypes, ({ pragma, type }) => {
-        return flatMap(serSeq[type], (ann) => {
+        return flatMap(serSeq[type], ann => {
           if (!isObject(ann)) {
             return [];
           }
@@ -142,7 +142,7 @@ export default function (_serSeq, options) {
           ann.notes = pragma
             ? {
                 ...ann.notes,
-                pragma: [pragma],
+                pragma: [pragma]
               }
             : ann.notes;
           return ann;
@@ -164,7 +164,7 @@ export default function (_serSeq, options) {
       lines.push(
         featureToGenbankString(feat, {
           ...options,
-          featurePadLength: longestFeatureTypeLength + 1,
+          featurePadLength: longestFeatureTypeLength + 1
         })
       );
     });
@@ -200,22 +200,23 @@ function createGenbankLocus(serSeq, options) {
     serSeq.sequence = serSeq.sequence.symbols.split("");
   }
 
-  let tmp;
   let dnaType;
   if (serSeq.isProtein) {
     dnaType = "";
   } else if (serSeq.type === "RNA") {
-    dnaType = serSeq?.doubleStranded ? 'RNA' : serSeq?.sequenceTypeFromLocus ?? "ss-RNA";
+    dnaType = serSeq?.doubleStranded
+      ? "RNA"
+      : serSeq?.sequenceTypeFromLocus ?? "ss-RNA";
   } else {
-    dnaType = serSeq?.doubleStranded ? 'DNA' : serSeq?.sequenceTypeFromLocus ?? "DNA";
+    dnaType = serSeq?.doubleStranded
+      ? "DNA"
+      : serSeq?.sequenceTypeFromLocus ?? "DNA";
   }
   const date = getCurrentDateString();
 
   let line = StringUtil.rpad("LOCUS", " ", 12);
   let nameToUse = serSeq.name || "Untitled_Sequence";
-  nameToUse = options.reformatSeqName
-    ? reformatName(nameToUse)
-    : nameToUse;
+  nameToUse = options.reformatSeqName ? reformatName(nameToUse) : nameToUse;
   line += StringUtil.rpad(nameToUse, " ", 16);
   line += " "; // T.H line 2778 of GenbankFormat.as col 29 space
   line += StringUtil.lpad(String(serSeq.sequence.length), " ", 11);
@@ -223,7 +224,7 @@ function createGenbankLocus(serSeq, options) {
   // if (strandType !== "") {
   // 	tmp =  strandType + "-";
   // } else {
-  tmp = "";
+  const tmp = "";
   // }
   line += StringUtil.lpad(tmp, " ", 3);
   line += StringUtil.rpad(dnaType, " ", 6);

package/src/jsonToJsonString.js

@@ -1,6 +1,6 @@
 import { omit } from "lodash";
 
-import cleanUpTeselagenJsonForExport from "./utils/cleanUpTeselagenJsonForExport"
+import cleanUpTeselagenJsonForExport from "./utils/cleanUpTeselagenJsonForExport";
 import { tidyUpSequenceData } from "@teselagen/sequence-utils";
 
 /**

package/src/sbolXmlToJson.js

@@ -2,7 +2,7 @@
 import validateSequenceArray from "./utils/validateSequenceArray";
 import searchWholeObjByName, {
   searchWholeObjByNameSimple,
-  searchWholeObjByNameSimpleArray,
+  searchWholeObjByNameSimpleArray
 } from "./utils/searchWholeObjByName";
 
 import { XMLParser } from "fast-xml-parser";
@@ -23,12 +23,12 @@ async function sbolXmlToJson(string, options) {
   let response = {
     parsedSequence: null,
     messages: [],
-    success: true,
+    success: true
   };
   try {
     const result = new XMLParser({
       isArray: () => true,
-      ignoreAttributes: false,
+      ignoreAttributes: false
     }).parse(string);
     const sbolJsonMatches = searchWholeObjByName("DnaComponent", result);
     if (sbolJsonMatches[0]) {
@@ -38,7 +38,7 @@ async function sbolXmlToJson(string, options) {
           response = {
             parsedSequence: null,
             messages: [],
-            success: true,
+            success: true
           };
           response.parsedSequence = parseSbolJson(
             sbolJsonMatches[0].value[i],
@@ -49,7 +49,7 @@ async function sbolXmlToJson(string, options) {
           console.error("error.stack: ", e.stack);
           resultArray.push({
             success: false,
-            messages: ["Error while parsing Sbol format"],
+            messages: ["Error while parsing Sbol format"]
           });
         }
         if (response.parsedSequence.features.length > 0) {
@@ -63,13 +63,13 @@ async function sbolXmlToJson(string, options) {
     } else {
       return onFileParsed({
         success: false,
-        messages: ["Error: XML is not valid Jbei or Sbol format"],
+        messages: ["Error: XML is not valid Jbei or Sbol format"]
       });
     }
   } catch (e) {
     return onFileParsed({
       success: false,
-      messages: ["Error parsing XML to JSON"],
+      messages: ["Error parsing XML to JSON"]
     });
   }
 }
@@ -124,11 +124,11 @@ function parseSbolJson(sbolJson, options) {
           end: parseInt(
             get(feature, "bioEnd[0]") - (options.inclusive1BasedEnd ? 0 : 1)
           ),
-          strand: get(feature, "strand[0]"), //+ or -
+          strand: get(feature, "strand[0]") //+ or -
           // notes: feature['seq:label'],
         };
       }
-    }),
+    })
   };
 }