@teselagen/bio-parsers 0.3.7 → 0.3.9

package/src/snapgeneToJson.js

@@ -13,7 +13,7 @@ import { get } from "lodash";
 import { XMLParser } from "fast-xml-parser";
 import extractFileExtension from "./utils/extractFileExtension";
 
-const Buffer = buffer.Buffer
+const Buffer = buffer.Buffer;
 
 async function snapgeneToJson(fileObj, options = {}) {
   try {
@@ -59,7 +59,7 @@ async function snapgeneToJson(fileObj, options = {}) {
       isDNA: !!(await unpack(2, "H")) && !isProtein,
       exportVersion: await unpack(2, "H"),
       importVersion: await unpack(2, "H"),
-      features: [],
+      features: []
     };
     while (offset <= arrayBuffer.byteLength) {
       // # READ THE WHOLE FILE, BLOCK BY BLOCK, UNTIL THE END
@@ -109,24 +109,24 @@ async function snapgeneToJson(fileObj, options = {}) {
           0: [1, "NONE"], // non-directional feature (in that case, the attribute is generally absent altogether)
           1: [1, "TOP"], // forward strand
           2: [-1, "BOTTOM"], // reverse strand
-          3: [1, "BOTH"], // bi-directional feature
+          3: [1, "BOTH"] // bi-directional feature
         };
         const xml = await read(block_size, "utf8");
         const b = new XMLParser({
           ignoreAttributes: false,
           attributeNamePrefix: "",
-          isArray: (name) => name === "Feature" || name === "Segment",
+          isArray: name => name === "Feature" || name === "Segment"
         }).parse(xml);
         const { Features: { Feature = [] } = {} } = b;
         data.features = [];
-        Feature.forEach((feat) => {
+        Feature.forEach(feat => {
           const { directionality, Segment = [], name, type } = feat;
           // let color;
           let maxStart = 0;
           let maxEnd = 0;
           const locations =
             Segment &&
-            Segment.map((seg) => {
+            Segment.map(seg => {
               if (!seg) throw new Error("invalid feature definition");
               const { range } = seg;
               // color = seg.color;
@@ -137,7 +137,7 @@ async function snapgeneToJson(fileObj, options = {}) {
               maxEnd = Math.max(maxEnd, end);
               return {
                 start,
-                end,
+                end
               };
             });
 
@@ -146,9 +146,11 @@ async function snapgeneToJson(fileObj, options = {}) {
             type,
             ...(locations?.length > 1 && { locations }),
             strand: directionality ? strand_dict[directionality][0] : 1,
-            arrowheadType: directionality ? strand_dict[directionality][1] : "NONE",
+            arrowheadType: directionality
+              ? strand_dict[directionality][1]
+              : "NONE",
             start: maxStart,
-            end: maxEnd,
+            end: maxEnd
             // color,
           });
         });
@@ -183,8 +185,8 @@ async function snapgeneToJson(fileObj, options = {}) {
     return [
       {
         success: false,
-        messages: ["Import Error: Invalid File"],
-      },
+        messages: ["Import Error: Invalid File"]
+      }
     ];
   }
 }
@@ -193,7 +195,7 @@ function getStartAndEndFromRangeString(rangestring) {
   const [start, end] = rangestring.split("-");
   return {
     start: start - 1,
-    end: end - 1,
+    end: end - 1
   };
 }
 

package/src/utils/NameUtils.js

@@ -6,5 +6,5 @@
  * @returns {string} New name.
  */
 export const reformatName = function (pName) {
-  return pName.toString().replace(/ /g, '_');
+  return pName.toString().replace(/ /g, "_");
 };

package/src/utils/ParserUtil.js

@@ -1,93 +1,91 @@
 const ParserUtil = {};
-ParserUtil.postProcessGenbankFeature = function(feat) {
-	let name = null;
-	// let nameIndex = null;
-
-	// let hasName = false;
-	let usingLabel = false;
-	let usingGene = false;
-
-	for (let j = 0; j < feat.notes.length; j++) {
-		const note = feat.notes[j];
-		const key = note.name;
-		const value = note.value;
-
-		// SET THE LABEL FIELD. DO NOT STORE AS AN ATTRIBUTE
-
-		if (this.isAGenbankFeatureLabel(key)) {
-			// Priority for name attributes is: 'label' > 'gene' > 'organism'.
-			// We check to see if the current name is from a lower-priority
-			// attribute. If it is, we store it as an attribute and then
-			// replace it with the current higher-priority attribute.
-
-			if (key === "label") {
-				// Label has top priority.
-
-				name = value;
-				// nameIndex = j;
-
-				usingLabel = true;
-			}
-			else if (key === "gene") {
-
-				// If we're not using the label for the name, use the
-				// current 'gene' attribute. If we are using label for
-				// the name, just save the current attribute as a normal
-				// attribute.
-				if (!usingLabel) {
-
-					name = value;
-					// nameIndex = j;
-
-					usingGene = true;
-				}
-			}
-			else if (!usingLabel && !usingGene) {
-				// If we don't have a label from either a 'gene' or a
-				// 'label' field, use the current field as the name.
-
-				name = value;
-				// nameIndex = j;
-
-			}
-
-			// hasName = true;
-		}
-	}
-
-	feat.name = name || "";
-	// if(nameIndex !== null) {
-	// 	feat.notes.splice(nameIndex, 1);
-	// }
-	//
-	// if(feat.locations.length > 0) {
-	// 	var loc = feat.locations[0];
-	// 	feat.start = loc.start;
-	// 	feat.end = loc.end;
-	// }
-	// else {
-	// 	feat.start = null;
-	// 	feat.end = null;
-	// }
-
-	return feat;
+ParserUtil.postProcessGenbankFeature = function (feat) {
+  let name = null;
+  // let nameIndex = null;
+
+  // let hasName = false;
+  let usingLabel = false;
+  let usingGene = false;
+
+  for (let j = 0; j < feat.notes.length; j++) {
+    const note = feat.notes[j];
+    const key = note.name;
+    const value = note.value;
+
+    // SET THE LABEL FIELD. DO NOT STORE AS AN ATTRIBUTE
+
+    if (this.isAGenbankFeatureLabel(key)) {
+      // Priority for name attributes is: 'label' > 'gene' > 'organism'.
+      // We check to see if the current name is from a lower-priority
+      // attribute. If it is, we store it as an attribute and then
+      // replace it with the current higher-priority attribute.
+
+      if (key === "label") {
+        // Label has top priority.
+
+        name = value;
+        // nameIndex = j;
+
+        usingLabel = true;
+      } else if (key === "gene") {
+        // If we're not using the label for the name, use the
+        // current 'gene' attribute. If we are using label for
+        // the name, just save the current attribute as a normal
+        // attribute.
+        if (!usingLabel) {
+          name = value;
+          // nameIndex = j;
+
+          usingGene = true;
+        }
+      } else if (!usingLabel && !usingGene) {
+        // If we don't have a label from either a 'gene' or a
+        // 'label' field, use the current field as the name.
+
+        name = value;
+        // nameIndex = j;
+      }
+
+      // hasName = true;
+    }
+  }
+
+  feat.name = name || "";
+  // if(nameIndex !== null) {
+  // 	feat.notes.splice(nameIndex, 1);
+  // }
+  //
+  // if(feat.locations.length > 0) {
+  // 	var loc = feat.locations[0];
+  // 	feat.start = loc.start;
+  // 	feat.end = loc.end;
+  // }
+  // else {
+  // 	feat.start = null;
+  // 	feat.end = null;
+  // }
+
+  return feat;
 };
 
-
-
 /**
  * isAFeatureLabel
  * @param {string} name Name of a attribute or qualifier
  * @return {boolean} isALabel
  */
-ParserUtil.isAGenbankFeatureLabel = function(name) {
-	if (name === "label" || name === "name" || name === "ApEinfo_label" ||
-		name === "note" || name === "gene" || name === "organism" || name === "locus_tag") {
-
-		return true;
-	}
-	else {
-		return false;
-	}
+ParserUtil.isAGenbankFeatureLabel = function (name) {
+  if (
+    name === "label" ||
+    name === "name" ||
+    name === "ApEinfo_label" ||
+    name === "note" ||
+    name === "gene" ||
+    name === "organism" ||
+    name === "locus_tag"
+  ) {
+    return true;
+  } else {
+    return false;
+  }
 };
 export default ParserUtil;

package/src/utils/cleanUpTeselagenJsonForExport.js

@@ -1,13 +1,12 @@
 import { cloneDeep, forEach } from "lodash";
 
 export default function cleanUpTeselagenJsonForExport(tgJson) {
-	const seqData = cloneDeep(tgJson);
-	if (!seqData) return seqData
-	delete seqData.cutsites;
-	delete seqData.orfs;
-	forEach(seqData.translations,(t)=>{
-		delete t.aminoAcids
-	})
-	return seqData
+  const seqData = cloneDeep(tgJson);
+  if (!seqData) return seqData;
+  delete seqData.cutsites;
+  delete seqData.orfs;
+  forEach(seqData.translations, t => {
+    delete t.aminoAcids;
+  });
+  return seqData;
 }
-

package/src/utils/constants.js

@@ -1,24 +1,24 @@
-export const untitledSequenceName = 'Untitled Sequence';
+export const untitledSequenceName = "Untitled Sequence";
 
 export const gbDivisions = {
-    // https://www.ncbi.nlm.nih.gov/Sitemap/samplerecord.html#GenBankDivisionB
-    PRI: true,  //- primate sequences
-    ROD: true,  //- rodent sequences
-    MAM: true,  //- other mammalian sequences
-    VRT: true,  //- other vertebrate sequences
-    INV: true,  //- invertebrate sequences
-    PLN: true,  //- plant, fungal, and algal sequences
-    BCT: true,  //- bacterial sequences
-    VRL: true,  //- viral sequences
-    PHG: true,  //- bacteriophage sequences
-    SYN: true,  //- synthetic sequences
-    UNA: true,  //- unannotated sequences
-    EST: true,  //- EST sequences (expressed sequence tags)
-    PAT: true,  //- patent sequences
-    STS: true,  //- STS sequences (sequence tagged sites)
-    GSS: true,  //- GSS sequences (genome survey sequences)
-    HTG: true,  //- HTG sequences (high-throughput genomic sequences)
-    HTC: true,  //- unfinished high-throughput cDNA sequencing
-    ENV: true,  //- environmental sampling sequences
-    CON: true,  //- sequence assembly instructions on how to construct contigs from multiple GenBank records.
-  }
+  // https://www.ncbi.nlm.nih.gov/Sitemap/samplerecord.html#GenBankDivisionB
+  PRI: true, //- primate sequences
+  ROD: true, //- rodent sequences
+  MAM: true, //- other mammalian sequences
+  VRT: true, //- other vertebrate sequences
+  INV: true, //- invertebrate sequences
+  PLN: true, //- plant, fungal, and algal sequences
+  BCT: true, //- bacterial sequences
+  VRL: true, //- viral sequences
+  PHG: true, //- bacteriophage sequences
+  SYN: true, //- synthetic sequences
+  UNA: true, //- unannotated sequences
+  EST: true, //- EST sequences (expressed sequence tags)
+  PAT: true, //- patent sequences
+  STS: true, //- STS sequences (sequence tagged sites)
+  GSS: true, //- GSS sequences (genome survey sequences)
+  HTG: true, //- HTG sequences (high-throughput genomic sequences)
+  HTC: true, //- unfinished high-throughput cDNA sequencing
+  ENV: true, //- environmental sampling sequences
+  CON: true //- sequence assembly instructions on how to construct contigs from multiple GenBank records.
+};

package/src/utils/convertOldSequenceDataToNewDataType.js

@@ -1,4 +1,4 @@
-import { isRangeWithinRange } from '@teselagen/range-utils';
+import { isRangeWithinRange } from "@teselagen/range-utils";
 
 export default function convertOldSequenceDataToNewDataType(
   oldTeselagenJson,
@@ -7,7 +7,7 @@ export default function convertOldSequenceDataToNewDataType(
   if (opts && opts.splitLocations) {
     //after the file has been parsed, but before it's been saved, check for features with multiple locations and split them
     oldTeselagenJson &&
-      oldTeselagenJson.features.forEach(function(feature) {
+      oldTeselagenJson.features.forEach(function (feature) {
         if (feature.locations && feature.locations[0]) {
           if (feature.locations.length > 1) {
             for (let i = 1; i < feature.locations.length; i++) {
@@ -31,11 +31,10 @@ export default function convertOldSequenceDataToNewDataType(
         }
         delete feature.locations;
       });
-
   } else {
     //mange locations
     oldTeselagenJson &&
-      oldTeselagenJson.features.forEach(function(feature) {
+      oldTeselagenJson.features.forEach(function (feature) {
         if (feature.locations && feature.locations[0]) {
           //set the new starts and ends
           feature.start = feature.locations[0].start;
@@ -53,7 +52,7 @@ export default function convertOldSequenceDataToNewDataType(
               delete feature.locations;
             }
           } else {
-            delete feature.locations
+            delete feature.locations;
           }
         }
       });
@@ -61,4 +60,4 @@ export default function convertOldSequenceDataToNewDataType(
   if (Array.isArray(oldTeselagenJson.sequence)) {
     oldTeselagenJson.sequence = oldTeselagenJson.sequence.join("");
   }
-};
+}

package/src/utils/createInitialSequence.js

@@ -1,14 +1,16 @@
 import { untitledSequenceName } from "./constants";
 
 export default function createInitialSequence(options) {
-    options = options || {}
-    return {
-        messages: [],
-        success: true,
-        parsedSequence: {
-            features: [],
-            name: (options.fileName && options.fileName.replace(/\.[^/.]+$/, "")) || untitledSequenceName,
-            sequence: ''
-        }
-    };
-};
+  options = options || {};
+  return {
+    messages: [],
+    success: true,
+    parsedSequence: {
+      features: [],
+      name:
+        (options.fileName && options.fileName.replace(/\.[^/.]+$/, "")) ||
+        untitledSequenceName,
+      sequence: ""
+    }
+  };
+}

package/src/utils/extractFileExtension.js

@@ -1,14 +1,12 @@
 export default function extractFileExtension(name) {
-	if (typeof name === 'string') {
-		let ext = "";
-		const match = name.match(/\.(\w+)$/);
-		if (match && match[1]) {
-			ext = match[1];
-		}
-		return ext;
-	}
-	else {
-		return "";
-	}
-};
-
+  if (typeof name === "string") {
+    let ext = "";
+    const match = name.match(/\.(\w+)$/);
+    if (match && match[1]) {
+      ext = match[1];
+    }
+    return ext;
+  } else {
+    return "";
+  }
+}

package/src/utils/flattenSequenceArray.js

@@ -1,17 +1,17 @@
-import convertOldSequenceDataToNewDataType from './convertOldSequenceDataToNewDataType.js';
+import convertOldSequenceDataToNewDataType from "./convertOldSequenceDataToNewDataType.js";
 
 export default function flattenSequenceArray(parsingResultArray, opts) {
-    if (parsingResultArray) {
-        if (!Array.isArray(parsingResultArray)) {
-            //wrap the parsingResult into an array if it isn't one already
-            parsingResultArray = [parsingResultArray];
-        }
-        //should convert the old data type to the new data type (flattened sequence)
-        parsingResultArray.forEach(function(parsingResult) {
-            if (parsingResult.success) {
-                convertOldSequenceDataToNewDataType(parsingResult.parsedSequence, opts);
-            }
-        });
+  if (parsingResultArray) {
+    if (!Array.isArray(parsingResultArray)) {
+      //wrap the parsingResult into an array if it isn't one already
+      parsingResultArray = [parsingResultArray];
     }
-    return parsingResultArray;
-};
+    //should convert the old data type to the new data type (flattened sequence)
+    parsingResultArray.forEach(function (parsingResult) {
+      if (parsingResult.success) {
+        convertOldSequenceDataToNewDataType(parsingResult.parsedSequence, opts);
+      }
+    });
+  }
+  return parsingResultArray;
+}

package/src/utils/getArrayBufferFromFile.js

@@ -1,5 +1,5 @@
-import { Buffer } from 'buffer';
-import isBrowser from './isBrowser';
+import { Buffer } from "buffer";
+import isBrowser from "./isBrowser";
 
 export default function getArrayBufferFromFile(file) {
   if (!isBrowser) {
@@ -9,11 +9,11 @@ export default function getArrayBufferFromFile(file) {
 
   const reader = new window.FileReader();
   return new Promise((resolve, reject) => {
-    reader.onload = (e) => {
+    reader.onload = e => {
       resolve(e.target.result);
     };
-    reader.onerror = (err) => {
-      console.error('err:', err);
+    reader.onerror = err => {
+      console.error("err:", err);
       reject(err);
     };
     reader.readAsArrayBuffer(

package/src/utils/isBrowser.js

@@ -1 +1,2 @@
-export default typeof window !== 'undefined' && typeof window.document !== 'undefined';
+export default typeof window !== "undefined" &&
+  typeof window.document !== "undefined";

package/src/utils/parseUracilFeatures.js

@@ -5,9 +5,9 @@ export default function parseUracilFeatures(sequenceBps, featureList = []) {
       name: "tg_uracil",
       strand: 1,
       start: index,
-      end: index,
+      end: index
     });
     return u === "U" ? "T" : "t";
   });
-  return cleanedBps
+  return cleanedBps;
 }

package/src/utils/pragmasAndTypes.js

@@ -1,5 +1,6 @@
 export default [
-  { //primers don't need a pragma because they already have a feature type of primer_bind
+  {
+    //primers don't need a pragma because they already have a feature type of primer_bind
     type: "primers"
   },
   {
@@ -18,4 +19,4 @@ export default [
     pragma: "j5_lineage_annotation",
     type: "lineageAnnotations"
   }
-]
+];

package/src/utils/searchWholeObjByName.js

@@ -16,7 +16,7 @@ class Match {
   logValue() {
     const val = this.value;
     // if value is an object then just toString it
-    const isPrimitive = (x) => Object(x) !== x;
+    const isPrimitive = x => Object(x) !== x;
     return isPrimitive(val) || Array.isArray(val) ? val : {}.toString.call(val);
   }
 
@@ -39,7 +39,7 @@ export default function searchWholeObjByName(what, where) {
 
   const matches = [];
   matches.log = function () {
-    this.forEach((m) => m.log());
+    this.forEach(m => m.log());
   };
 
   // a non-recursive solution to avoid call stack limits
@@ -77,7 +77,7 @@ export default function searchWholeObjByName(what, where) {
               path: `${path}.${prop}`,
               obj: where,
               prop,
-              type,
+              type
             });
             matches.push(match);
           }

package/src/utils/splitStringIntoLines.js

@@ -1,13 +1,14 @@
 export default function splitStringIntoLines(string) {
-	let lines = [];
-	if (string === "") {
-		return lines;
-	}
-	else {
-		lines = string.split(/\r?\n/);
-		if (lines.length == 1) { //tnr: not sure why this check is being made... but keeping it in because it is probably doing something
-			lines = string.split('\\n');
-		}
-		return lines;
-	}
-};
+  let lines = [];
+  if (string === "") {
+    return lines;
+  } else {
+    lines = string.split(/\r?\n/);
+    // eslint-disable-next-line eqeqeq
+    if (lines.length == 1) {
+      //tnr: not sure why this check is being made... but keeping it in because it is probably doing something
+      lines = string.split("\\n");
+    }
+    return lines;
+  }
+}