sdf-parser - npm Package Compare versions

Comparing version 3.1.0 to 4.0.0

package.json

 {
   "name": "sdf-parser",
-  "version": "3.1.0",
+  "version": "4.0.0",
   "description": "SDF parser",
@@ -12,4 +12,5 @@ "main": "./src/index.js",
     "eslint-fix": "npm run eslint -- --fix",
-    "test": "jest && npm run eslint",
-    "build": "cheminfo build --root SDFParser"
+    "test": "npm run test-coverage && npm run eslint",
+    "test-coverage": "jest --coverage",
+    "test-only": "jest"
   },
@@ -37,17 +38,18 @@ "browser": {
   "devDependencies": {
+    "babel-eslint": "^10.0.1",
     "callback-stream": "^1.1.0",
-    "cheminfo-tools": "^1.20.2",
-    "eslint": "^4.16.0",
-    "eslint-config-cheminfo": "^1.14.1",
-    "eslint-plugin-no-only-tests": "^2.0.0",
-    "jest": "^22.1.4",
-    "openchemlib": "^5.5.0",
-    "should": "^13.2.1"
+    "eslint": "^5.16.0",
+    "eslint-config-cheminfo": "^1.20.1",
+    "eslint-plugin-import": "^2.17.3",
+    "eslint-plugin-jest": "^22.6.4",
+    "jest": "^24.8.0",
+    "openchemlib": "^7.1.0"
   },
   "dependencies": {
-    "multipipe": "^2.0.1",
-    "split2": "^2.2.0",
-    "through2": "^2.0.3",
-    "through2-filter": "^2.0.0"
+    "@targos/pumpify": "^2.0.0",
+    "readable-stream": "^3.4.0",
+    "split2": "^3.1.1",
+    "through2": "^3.0.1",
+    "through2-filter": "^3.0.0"
   }
 }

README.md

 # sdf-parser
 
-  [![NPM version][npm-image]][npm-url]
-  [![build status][travis-image]][travis-url]
-  [![David deps][david-image]][david-url]
-  [![npm download][download-image]][download-url]
+[![NPM version][npm-image]][npm-url]
+[![build status][travis-image]][travis-url]
+[![npm download][download-image]][download-url]
 
-Allow to parse a SDF file and convert it to an array of objects
+Allow to parse a SDF file and convert it to an array of objects.
 
@@ -17,4 +16,4 @@ ## Use of the package
 In node script:
+
 ```js
-
 // allows to parse a file test.sdf that would be present in the same directory
@@ -29,3 +28,2 @@
 console.log(result);
-
 ```
@@ -36,25 +34,27 @@
 options:
-* exclude : array of string containing the fields to discard
-* include : array of string containing the fields to keep
-* modifiers : object of functions that need to be converted during the parsing
-* filter : function that allows to filter the result
-* mixedEOL : if set to true will try to deal with mixed End Of Line separator
-* dynamicTyping : convert fields containing only number to numbers (default: true)
+
+- exclude : array of string containing the fields to discard
+- include : array of string containing the fields to keep
+- modifiers : object of functions that need to be converted during the parsing
+- filter : function that allows to filter the result
+- mixedEOL : if set to true will try to deal with mixed End Of Line separator
+- dynamicTyping : convert fields containing only number to numbers (default: true)
+
 ## Advanced example with filtering and modifiers
 
-```
+```js
 var result = parse(sdf, {
-    exclude:["Number of H-Donors"],
-    include:["Number of H-Donors",'CLogP','Code'],
-    modifiers: {
-        CLogP: function(field) {
-            return {
-                low: field*1-0.2,
-                high: field*1+0.2
-            }
-        }
-    },
-    filter: function(entry) {
-        return (entry.CLogP && entry.CLogP.low>4);
+  exclude: ['Number of H-Donors'],
+  include: ['Number of H-Donors', 'CLogP', 'Code'],
+  modifiers: {
+    CLogP: function(field) {
+      return {
+        low: field * 1 - 0.2,
+        high: field * 1 + 0.2
+      };
     }
+  },
+  filter: function(entry) {
+    return entry.CLogP && entry.CLogP.low > 4;
+  }
 });
@@ -65,3 +65,3 @@ ```
 
-This API is only available on Node.js
+This API is only available on Node.js.
 
@@ -78,8 +78,8 @@ ### molecules(options)
 ```js
-const stream = require('sdf-parser').stream;
+const { stream } = require('sdf-parser');
 fs.createReadStream('test.sdf')
-    .pipe(stream.molecules())
-    .on('data', (molecule) => {
-        console.log(molecule.molfile);
-    });
+  .pipe(stream.molecules())
+  .on('data', (molecule) => {
+    console.log(molecule.molfile);
+  });
 ```
@@ -92,8 +92,8 @@
 ```js
-const stream = require('sdf-parser').stream;
+const { stream } = require('sdf-parser');
 fs.createReadStream('test.sdf')
-    .pipe(stream.entries())
-    .on('data', (entry) => {
-        // sdf entry as a string
-    });
+  .pipe(stream.entries())
+  .on('data', (entry) => {
+    // sdf entry as a string
+  });
 ```
@@ -103,3 +103,3 @@
 
-  [MIT](./LICENSE)
+[MIT](./LICENSE)
 
@@ -110,5 +110,3 @@ [npm-image]: https://img.shields.io/npm/v/sdf-parser.svg?style=flat-square
 [travis-url]: https://travis-ci.org/cheminfo-js/sdf-parser
-[david-image]: https://img.shields.io/david/cheminfo-js/sdf-parser.svg?style=flat-square
-[david-url]: https://david-dm.org/cheminfo-js/sdf-parser
 [download-image]: https://img.shields.io/npm/dm/sdf-parser.svg?style=flat-square
 [download-url]: https://www.npmjs.com/package/sdf-parser

src/parse.js

 'use strict';
 
 function parse(sdf, options = {}) {
-    const {
-        include,
-        exclude,
-        filter,
-        modifiers = {},
-        forEach = {},
-        dynamicTyping = true
-    } = options;
+  const {
+    include,
+    exclude,
+    filter,
+    modifiers = {},
+    forEach = {},
+    dynamicTyping = true
+  } = options;
 
-    if (typeof sdf !== 'string') {
-        throw new TypeError('Parameter "sdf" must be a string');
-    }
+  if (typeof sdf !== 'string') {
+    throw new TypeError('Parameter "sdf" must be a string');
+  }
 
-    var eol = '\n';
-    if (options.mixedEOL) {
-        sdf = sdf.replace(/\r\n/g, '\n');
-        sdf = sdf.replace(/\r/g, '\n');
-    } else {
-        // we will find the delimiter in order to be much faster and not use regular expression
-        var header = sdf.substr(0, 1000);
-        if (header.indexOf('\r\n') > -1) {
-            eol = '\r\n';
-        } else if (header.indexOf('\r') > -1) {
-            eol = '\r';
-        }
+  var eol = '\n';
+  if (options.mixedEOL) {
+    sdf = sdf.replace(/\r\n/g, '\n');
+    sdf = sdf.replace(/\r/g, '\n');
+  } else {
+    // we will find the delimiter in order to be much faster and not use regular expression
+    var header = sdf.substr(0, 1000);
+    if (header.indexOf('\r\n') > -1) {
+      eol = '\r\n';
+    } else if (header.indexOf('\r') > -1) {
+      eol = '\r';
     }
+  }
 
-    var sdfParts = sdf.split(new RegExp(eol + '\\$\\$\\$\\$.*' + eol));
-    var molecules = [];
-    var labels = {};
+  var sdfParts = sdf.split(new RegExp(`${eol}\\$\\$\\$\\$.*${eol}`));
+  var molecules = [];
+  var labels = {};
 
-    var start = Date.now();
+  var start = Date.now();
 
-    for (var i = 0; i < sdfParts.length; i++) {
-        var sdfPart = sdfParts[i];
-        var parts = sdfPart.split(eol + '>');
-        if (parts.length > 0 && parts[0].length > 5) {
-            var molecule = {};
-            var currentLabels = [];
-            molecule.molfile = parts[0] + eol;
-            for (var j = 1; j < parts.length; j++) {
-                var lines = parts[j].split(eol);
-                var from = lines[0].indexOf('<');
-                var to = lines[0].indexOf('>');
-                var label = lines[0].substring(from + 1, to);
-                currentLabels.push(label);
-                if (!labels[label]) {
-                    labels[label] = {
-                        counter: 0,
-                        isNumeric: dynamicTyping,
-                        keep: false
-                    };
-                    if (
-                        (!exclude || exclude.indexOf(label) === -1) &&
-                        (!include || include.indexOf(label) > -1)
-                    ) {
-                        labels[label].keep = true;
-                        if (modifiers[label]) labels[label].modifier = modifiers[label];
-                        if (forEach[label]) labels[label].forEach = forEach[label];
-                    }
-                }
-                if (labels[label].keep) {
-                    for (var k = 1; k < lines.length - 1; k++) {
-                        if (molecule[label]) {
-                            molecule[label] += eol + lines[k];
-                        } else {
-                            molecule[label] = lines[k];
-                        }
-                    }
-                    if (labels[label].modifier) {
-                        var modifiedValue = labels[label].modifier(molecule[label]);
-                        if (modifiedValue === undefined || modifiedValue === null) {
-                            delete molecule[label];
-                        } else {
-                            molecule[label] = modifiedValue;
-                        }
-                    }
-                    if (labels[label].isNumeric) {
-                        if (!isFinite(molecule[label]) || molecule[label].match(/^0[0-9]/)) {
-                            labels[label].isNumeric = false;
-                        }
-                    }
-                }
+  for (var i = 0; i < sdfParts.length; i++) {
+    var sdfPart = sdfParts[i];
+    var parts = sdfPart.split(`${eol}>`);
+    if (parts.length > 0 && parts[0].length > 5) {
+      var molecule = {};
+      var currentLabels = [];
+      molecule.molfile = parts[0] + eol;
+      for (var j = 1; j < parts.length; j++) {
+        var lines = parts[j].split(eol);
+        var from = lines[0].indexOf('<');
+        var to = lines[0].indexOf('>');
+        var label = lines[0].substring(from + 1, to);
+        currentLabels.push(label);
+        if (!labels[label]) {
+          labels[label] = {
+            counter: 0,
+            isNumeric: dynamicTyping,
+            keep: false
+          };
+          if (
+            (!exclude || exclude.indexOf(label) === -1) &&
+            (!include || include.indexOf(label) > -1)
+          ) {
+            labels[label].keep = true;
+            if (modifiers[label]) labels[label].modifier = modifiers[label];
+            if (forEach[label]) labels[label].forEach = forEach[label];
+          }
+        }
+        if (labels[label].keep) {
+          for (var k = 1; k < lines.length - 1; k++) {
+            if (molecule[label]) {
+              molecule[label] += eol + lines[k];
+            } else {
+              molecule[label] = lines[k];
             }
-            if (!filter || filter(molecule)) {
-                molecules.push(molecule);
-                // only now we can increase the counter
-                for (j = 0; j < currentLabels.length; j++) {
-                    var currentLabel = currentLabels[j];
-                    labels[currentLabel].counter++;
-                }
+          }
+          if (labels[label].modifier) {
+            var modifiedValue = labels[label].modifier(molecule[label]);
+            if (modifiedValue === undefined || modifiedValue === null) {
+              delete molecule[label];
+            } else {
+              molecule[label] = modifiedValue;
             }
-        }
-    }
-
-    // all numeric fields should be converted to numbers
-    for (label in labels) {
-        currentLabel = labels[label];
-        if (currentLabel.isNumeric) {
-            currentLabel.minValue = Infinity;
-            currentLabel.maxValue = -Infinity;
-            for (j = 0; j < molecules.length; j++) {
-                if (molecules[j][label]) {
-                    var value = parseFloat(molecules[j][label]);
-                    molecules[j][label] = value;
-                    if (value > currentLabel.maxValue) currentLabel.maxValue = value;
-                    if (value < currentLabel.minValue) currentLabel.minValue = value;
-                }
+          }
+          if (labels[label].isNumeric) {
+            if (
+              !isFinite(molecule[label]) ||
+              molecule[label].match(/^0[0-9]/)
+            ) {
+              labels[label].isNumeric = false;
             }
+          }
         }
+      }
+      if (!filter || filter(molecule)) {
+        molecules.push(molecule);
+        // only now we can increase the counter
+        for (j = 0; j < currentLabels.length; j++) {
+          var currentLabel = currentLabels[j];
+          labels[currentLabel].counter++;
+        }
+      }
     }
+  }
 
-    // we check that a label is in all the records
-    for (var key in labels) {
-        if (labels[key].counter === molecules.length) {
-            labels[key].always = true;
-        } else {
-            labels[key].always = false;
+  // all numeric fields should be converted to numbers
+  for (label in labels) {
+    currentLabel = labels[label];
+    if (currentLabel.isNumeric) {
+      currentLabel.minValue = Infinity;
+      currentLabel.maxValue = -Infinity;
+      for (j = 0; j < molecules.length; j++) {
+        if (molecules[j][label]) {
+          var value = parseFloat(molecules[j][label]);
+          molecules[j][label] = value;
+          if (value > currentLabel.maxValue) currentLabel.maxValue = value;
+          if (value < currentLabel.minValue) currentLabel.minValue = value;
         }
+      }
     }
+  }
 
-    var statistics = [];
-    for (key in labels) {
-        var statistic = labels[key];
-        statistic.label = key;
-        statistics.push(statistic);
+  // we check that a label is in all the records
+  for (var key in labels) {
+    if (labels[key].counter === molecules.length) {
+      labels[key].always = true;
+    } else {
+      labels[key].always = false;
     }
+  }
 
-    return {
-        time: Date.now() - start,
-        molecules: molecules,
-        labels: Object.keys(labels),
-        statistics: statistics
-    };
+  var statistics = [];
+  for (key in labels) {
+    var statistic = labels[key];
+    statistic.label = key;
+    statistics.push(statistic);
+  }
 
+  return {
+    time: Date.now() - start,
+    molecules: molecules,
+    labels: Object.keys(labels),
+    statistics: statistics
+  };
 }
 
 module.exports = parse;

src/stream.js

 'use strict';
 
-const combine = require('multipipe');
+const pipeline = require('@targos/pumpify');
 const split2 = require('split2');
@@ -10,43 +10,43 @@ const filter = require('through2-filter');
 
-const filterStream = filter.bind(null, {objectMode: true});
+const filterStream = filter.bind(null, { objectMode: true });
 function filterCb(chunk) {
-    return chunk.length > 1 && chunk.trim().length > 1;
+  return chunk.length > 1 && chunk.trim().length > 1;
 }
 
 function entries() {
-    return combine(
-        split2(/\r?\n\${4}.*\r?\n/),
-        filterStream(filterCb),
-        through2({objectMode: true}, function (value, encoding, callback) {
-            const eol = value.includes('\r\n') ? '\r\n' : '\n';
-            this.push(value + eol + '$$$$' + eol);
-            callback();
-        })
-    );
+  return pipeline.obj(
+    split2(/\r?\n\${4}.*\r?\n/),
+    filterStream(filterCb),
+    through2({ objectMode: true }, function (value, encoding, callback) {
+      const eol = value.includes('\r\n') ? '\r\n' : '\n';
+      this.push(`${value + eol}$$$$${eol}`);
+      callback();
+    })
+  );
 }
 
 function molecules(options) {
-    return combine(
-        entries(),
-        through2({objectMode: true}, function (value, encoding, callback) {
-            try {
-                const parsed = parse(value, options);
-                if (parsed.molecules.length === 1) {
-                    if (options && options.fullResult) {
-                        this.push(parsed);
-                    } else {
-                        this.push(parsed.molecules[0]);
-                    }
-                }
-                callback();
-            } catch (e) {
-                callback(e);
-            }
-        })
-    );
+  return pipeline.obj(
+    entries(),
+    through2({ objectMode: true }, function (value, encoding, callback) {
+      try {
+        const parsed = parse(value, options);
+        if (parsed.molecules.length === 1) {
+          if (options && options.fullResult) {
+            this.push(parsed);
+          } else {
+            this.push(parsed.molecules[0]);
+          }
+        }
+        callback();
+      } catch (e) {
+        callback(e);
+      }
+    })
+  );
 }
 
 module.exports = {
-    entries,
-    molecules
+  entries,
+  molecules
 };

No alert changes

Improved metrics

Total package byte prevSize

12358

increased by7.72%

Number of package files

8

increased by14.29%

Lines of code

184

increased by1.66%

Worsened metrics

Dependency count

5

increased by25%

Number of lines in readme file

105

decreased by-1.87%

Dependency changes

• + Added@targos/pumpify@^2.0.0

• + Addedreadable-stream@^3.4.0

• + Added@targos/pumpify@2.0.0(transitive)

• + Addedduplexify@4.1.3(transitive)

• + Addedend-of-stream@1.4.4(transitive)

• + Addedonce@1.4.0(transitive)

• + Addedpump@3.0.2(transitive)

• + Addedreadable-stream@3.6.2(transitive)

• + Addedsafe-buffer@5.2.1(transitive)

• + Addedsplit2@3.2.2(transitive)

• + Addedstream-shift@1.0.3(transitive)

• + Addedstring_decoder@1.3.0(transitive)

• + Addedthrough2@3.0.24.0.2(transitive)

• + Addedthrough2-filter@3.1.0(transitive)

• + Addedwrappy@1.0.2(transitive)

• - Removedmultipipe@^2.0.1

• - Removedcore-util-is@1.0.3(transitive)

• - Removedduplexer2@0.1.4(transitive)

• - Removedisarray@1.0.0(transitive)

• - Removedmultipipe@2.0.3(transitive)

• - Removedobject-assign@4.1.1(transitive)

• - Removedprocess-nextick-args@2.0.1(transitive)

• - Removedreadable-stream@2.3.8(transitive)

• - Removedsafe-buffer@5.1.2(transitive)

• - Removedsplit2@2.2.0(transitive)

• - Removedstring_decoder@1.1.1(transitive)

• - Removedthrough2@2.0.5(transitive)

• - Removedthrough2-filter@2.0.0(transitive)

• - Removedxtend@4.0.2(transitive)

• Updatedsplit2@^3.1.1

• Updatedthrough2@^3.0.1

• Updatedthrough2-filter@^3.0.0