sdf-parser 7.0.3 → 7.0.5

package/lib/index.js

@@ -43,8 +43,7 @@ function getEntriesBoundaries(string, substring, eol) {
 function getMolecule$1(sdfPart, labels, currentLabels, options) {
   let parts = sdfPart.split(`${options.eol}>`);
   if (parts.length === 0 || parts[0].length <= 5) return;
-  let molecule = {};
-  molecule.molfile = parts[0] + options.eol;
+  let molecule = { molfile: parts[0] + options.eol };
   for (let j = 1; j < parts.length; j++) {
     let lines = parts[j].split(options.eol);
     let from = lines[0].indexOf('<');
@@ -108,6 +107,7 @@ function getMolecule$1(sdfPart, labels, currentLabels, options) {
  * @param {object} [options.modifiers] - Object containing callbacks to apply on some specific fields
  * @param {boolean} [options.mixedEOL=false] - Set to true if you know there is a mixture between \r\n and \n
  * @param {string} [options.eol] - Specify the end of line character. Default will be the one found in the file
+ * @returns {object} - Object containing the molecules, the labels and the statistics
  */
 function parse(sdf, options = {}) {
   options = { ...options };
@@ -148,7 +148,7 @@ function parse(sdf, options = {}) {
 
   for (let i = 0; i < entriesBoundaries.length; i++) {
     let sdfPart = sdf.slice(...entriesBoundaries[i]);
-
+    if (sdfPart.length < 40) continue;
     let currentLabels = [];
     const molecule = getMolecule$1(sdfPart, labels, currentLabels, options);
     if (!molecule) continue;
@@ -224,14 +224,16 @@ class MolfileStream extends TransformStream {
           }
           const eolLength = this.#buffer[endOfDelimiter - 1] === '\r' ? 2 : 1;
           // need to remove the last eol because we will split on eol+'>' in getMolecule
-          controller.enqueue(this.#buffer.slice(begin, index - eolLength));
+          if (index - eolLength - begin > 40) {
+            controller.enqueue(this.#buffer.slice(begin, index - eolLength));
+          }
           index = endOfDelimiter + eolLength;
           begin = index;
         }
         this.#buffer = this.#buffer.slice(begin);
       },
       flush: (controller) => {
-        if (this.#buffer) {
+        if (this.#buffer && this.#buffer.length > 40) {
           controller.enqueue(this.#buffer);
         }
       },
@@ -253,7 +255,6 @@ async function* iterator(readStream, options = {}) {
 
   const moleculeStream = readStream.pipeThrough(new MolfileStream({ eol }));
   for await (const entry of moleculeStream) {
-    if (entry.length < 20) continue;
     const molecule = getMolecule(entry, {
       eol,
       dynamicTyping,
@@ -276,8 +277,7 @@ function getMolecule(sdfPart, options) {
   const { eol, dynamicTyping: dynamicTyping$1 } = options;
   let parts = sdfPart.split(`${eol}>`);
   if (parts.length === 0 || parts[0].length <= 5) return;
-  let molecule = {};
-  molecule.molfile = parts[0] + eol;
+  let molecule = { molfile: parts[0] + eol };
   for (let j = 1; j < parts.length; j++) {
     let lines = parts[j].split(eol);
     let from = lines[0].indexOf('<');

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sdf-parser",
-  "version": "7.0.3",
+  "version": "7.0.5",
   "description": "SDF parser",
   "main": "lib/index.js",
   "module": "src/index.js",
@@ -39,21 +39,19 @@
   },
   "homepage": "https://github.com/cheminfo/sdf-parser",
   "devDependencies": {
-    "@babel/plugin-transform-modules-commonjs": "^7.26.3",
-    "@types/node": "^22.13.5",
-    "@vitest/coverage-v8": "^3.0.7",
-    "babel-eslint": "^10.1.0",
+    "@types/node": "^25.2.3",
+    "@vitest/coverage-v8": "^4.0.18",
     "callback-stream": "^1.1.0",
-    "cheminfo-build": "^1.2.1",
+    "cheminfo-build": "^1.3.2",
     "eslint": "^9.21.0",
-    "eslint-config-cheminfo": "^13.0.0",
-    "file-collection": "^1.0.0",
-    "openchemlib": "^8.18.1",
-    "prettier": "^3.5.2",
-    "vitest": "^3.0.7"
+    "eslint-config-cheminfo": "^17.1.0",
+    "file-collection": "^6.6.0",
+    "openchemlib": "^9.20.0",
+    "prettier": "^3.8.1",
+    "vitest": "^4.0.18"
   },
   "dependencies": {
     "dynamic-typing": "^1.0.1",
-    "ensure-string": "^1.2.0"
+    "ensure-string": "^2.0.0"
   }
 }

package/src/MolfileStream.js

@@ -17,14 +17,16 @@ export class MolfileStream extends TransformStream {
           }
           const eolLength = this.#buffer[endOfDelimiter - 1] === '\r' ? 2 : 1;
           // need to remove the last eol because we will split on eol+'>' in getMolecule
-          controller.enqueue(this.#buffer.slice(begin, index - eolLength));
+          if (index - eolLength - begin > 40) {
+            controller.enqueue(this.#buffer.slice(begin, index - eolLength));
+          }
           index = endOfDelimiter + eolLength;
           begin = index;
         }
         this.#buffer = this.#buffer.slice(begin);
       },
       flush: (controller) => {
-        if (this.#buffer) {
+        if (this.#buffer && this.#buffer.length > 40) {
           controller.enqueue(this.#buffer);
         }
       },

package/src/iterator.js

@@ -16,7 +16,6 @@ export async function* iterator(readStream, options = {}) {
 
   const moleculeStream = readStream.pipeThrough(new MolfileStream({ eol }));
   for await (const entry of moleculeStream) {
-    if (entry.length < 20) continue;
     const molecule = getMolecule(entry, {
       eol,
       dynamicTyping,
@@ -39,8 +38,7 @@ function getMolecule(sdfPart, options) {
   const { eol, dynamicTyping } = options;
   let parts = sdfPart.split(`${eol}>`);
   if (parts.length === 0 || parts[0].length <= 5) return;
-  let molecule = {};
-  molecule.molfile = parts[0] + eol;
+  let molecule = { molfile: parts[0] + eol };
   for (let j = 1; j < parts.length; j++) {
     let lines = parts[j].split(eol);
     let from = lines[0].indexOf('<');

package/src/parse.js

@@ -13,6 +13,7 @@ import { getMolecule } from './util/getMolecule';
  * @param {object} [options.modifiers] - Object containing callbacks to apply on some specific fields
  * @param {boolean} [options.mixedEOL=false] - Set to true if you know there is a mixture between \r\n and \n
  * @param {string} [options.eol] - Specify the end of line character. Default will be the one found in the file
+ * @returns {object} - Object containing the molecules, the labels and the statistics
  */
 export function parse(sdf, options = {}) {
   options = { ...options };
@@ -53,7 +54,7 @@ export function parse(sdf, options = {}) {
 
   for (let i = 0; i < entriesBoundaries.length; i++) {
     let sdfPart = sdf.slice(...entriesBoundaries[i]);
-
+    if (sdfPart.length < 40) continue;
     let currentLabels = [];
     const molecule = getMolecule(sdfPart, labels, currentLabels, options);
     if (!molecule) continue;

package/src/util/getMolecule.js

@@ -9,8 +9,7 @@
 export function getMolecule(sdfPart, labels, currentLabels, options) {
   let parts = sdfPart.split(`${options.eol}>`);
   if (parts.length === 0 || parts[0].length <= 5) return;
-  let molecule = {};
-  molecule.molfile = parts[0] + options.eol;
+  let molecule = { molfile: parts[0] + options.eol };
   for (let j = 1; j < parts.length; j++) {
     let lines = parts[j].split(options.eol);
     let from = lines[0].indexOf('<');