@diplodoc/sentenizer - npm Package Compare versions

Comparing version 0.0.6 to 0.0.7

lib/index.d.ts

@@ -1,1 +0,1 @@
-export { sentenize } from './sentenize';
+export declare function sentenize(text: string): string[];

lib/index.js

@@ -25,4 +25,2 @@ var __defProp = Object.defineProperty;
 module.exports = __toCommonJS(src_exports);
-
-// src/sentenize.ts
 var import_ramda8 = require("ramda");
@@ -33,167 +31,11 @@
 
-// src/constants.ts
+// src/constants/markers.ts
 var SENTENCE_END_MARKERS = ".?!\u2026";
-var QUOTATION_GENERIC_MARKERS = `\xAB"\u201E'`;
-var QUOTATION_CLOSE_MARKERS = '\xBB"\u201D\u2019';
+var QUOTATION_GENERIC_MARKERS = `"\u201E'`;
+var QUOTATION_CLOSE_MARKERS = "\xBB\u201D\u2019";
 var BRACKETS_CLOSE_MARKERS = "\\)\\]\\}>";
+
+// src/constants/parameters.ts
 var WINDOW_WIDTH = 10;
 
-// src/lenses/index.ts
-var import_ramda = require("ramda");
-var first = () => (0, import_ramda.lensIndex)(0);
-var second = () => (0, import_ramda.lensIndex)(1);
-var last = () => (0, import_ramda.lensIndex)(-1);
-
-// src/parsers/index.ts
-var firstString = first();
-var fst = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), (0, import_ramda2.view)(firstString));
-var secondString = second();
-var snd = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), (0, import_ramda2.view)(secondString));
-var lastString = last();
-var lst = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), (0, import_ramda2.view)(lastString));
-var sentencePattern = `([^${SENTENCE_END_MARKERS}]*?[${SENTENCE_END_MARKERS}]+)`;
-var senteceFlags = "gmu";
-var sentenceRegExp = new RegExp(sentencePattern, senteceFlags);
-var sentences = (0, import_ramda2.compose)((0, import_ramda2.filter)(Boolean), (0, import_ramda2.split)(sentenceRegExp));
-var sentenceDelimitersPattern = `([${SENTENCE_END_MARKERS}]+)$`;
-var sentenceDelimitersFlags = "gmu";
-var sentenceDelimitersRegExp = new RegExp(sentenceDelimitersPattern, sentenceDelimitersFlags);
-var words = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), (0, import_ramda2.replace)(sentenceDelimitersRegExp)(""));
-var delimiters = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), fst, (0, import_ramda2.match)(sentenceDelimitersRegExp));
-var fstTokenPattern = /^\s*([^\s]+?)(?=\s|$)/;
-var fstTokenFlags = "mu";
-var fstTokenRegExp = new RegExp(fstTokenPattern, fstTokenFlags);
-var fstToken = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), snd, (0, import_ramda2.match)(fstTokenRegExp));
-var fstWord = (0, import_ramda2.compose)(fstToken, words);
-var lstTokenPattern = /([^\s]+)\s*$/;
-var lstTokenFlags = "mu";
-var lstTokenRegExp = new RegExp(lstTokenPattern, lstTokenFlags);
-var lstToken = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), snd, (0, import_ramda2.match)(lstTokenRegExp));
-var nonAlphaStartPattern = /^[^\wа-яА-Я]*/;
-var nonAlphaStartFlags = "gmu";
-var nonAlphaStartRegExp = new RegExp(nonAlphaStartPattern, nonAlphaStartFlags);
-var omitNonAlphaStart = (0, import_ramda2.replace)(nonAlphaStartRegExp, "");
-var lstWord = (0, import_ramda2.compose)(lstToken, words);
-var fstChars = (width = WINDOW_WIDTH) => {
-  const fstCharsPattern = `^[\\s\\S]{0,${width}}`;
-  const fstCharsFlags = "gmu";
-  const fstCharsRegExp = new RegExp(fstCharsPattern, fstCharsFlags);
-  return (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), fst, (0, import_ramda2.match)(fstCharsRegExp));
-};
-var lstChars = (width = WINDOW_WIDTH) => {
-  const lstCharsPattern = `.{0,${width}}$`;
-  const lstCharsFlags = "gmu";
-  const lstCharsRegExp = new RegExp(lstCharsPattern, lstCharsFlags);
-  return (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), fst, (0, import_ramda2.match)(lstCharsRegExp));
-};
-var spacePrefixPattern = /^\s/;
-var spacePrefixFlags = "gmu";
-var spacePrefixRegExp = new RegExp(spacePrefixPattern, spacePrefixFlags);
-var spacePrefix = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), fst, (0, import_ramda2.match)(spacePrefixRegExp));
-var spaceSuffixPattern = /\s$/;
-var spaceSuffixFlags = "mu";
-var spaceSuffixRegExp = new RegExp(spaceSuffixPattern, spaceSuffixFlags);
-var spaceSuffix = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), fst, (0, import_ramda2.match)(spaceSuffixRegExp));
-var quotationGenericPrefixPattern = `^([${QUOTATION_GENERIC_MARKERS}]+)`;
-var quotationGenericPrefixFlags = "mu";
-var quotationGenericPrefixRegExp = new RegExp(
-  quotationGenericPrefixPattern,
-  quotationGenericPrefixFlags
-);
-var quotationGenericPrefix = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), snd, (0, import_ramda2.match)(quotationGenericPrefixRegExp));
-var quotationClosePrefixPattern = `^([${QUOTATION_CLOSE_MARKERS}]+)`;
-var quotationClosePrefixFlags = "mu";
-var quotationClosePrefixRegExp = new RegExp(
-  quotationClosePrefixPattern,
-  quotationClosePrefixFlags
-);
-var quotationClosePrefix = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), snd, (0, import_ramda2.match)(quotationClosePrefixRegExp));
-var delimiterPrefixPattern = `^([${SENTENCE_END_MARKERS}]+)`;
-var delimiterPrefixFlags = "mu";
-var delimiterPrefixRegExp = new RegExp(delimiterPrefixPattern, delimiterPrefixFlags);
-var delimiterPrefix = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), snd, (0, import_ramda2.match)(delimiterPrefixRegExp));
-var bracketsClosePrefixPattern = `^([${BRACKETS_CLOSE_MARKERS}]+)`;
-var bracketsClosePrefixFlags = "mu";
-var bracketsClosePrefixRegExp = new RegExp(bracketsClosePrefixPattern, bracketsClosePrefixFlags);
-var bracketsClosePrefix = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), snd, (0, import_ramda2.match)(bracketsClosePrefixRegExp));
-var spacesPattern = /^(\s+)$/;
-var spacesFlags = "gmu";
-var spacesRegExp = new RegExp(spacesPattern, spacesFlags);
-var spaces = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), fst, (0, import_ramda2.match)(spacesRegExp));
-var dotSuffixPattern = /[^.](\.)$/;
-var dotSuffixFlags = "mu";
-var dotSuffixRegExp = new RegExp(dotSuffixPattern, dotSuffixFlags);
-var dotSuffix = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), snd, (0, import_ramda2.match)(dotSuffixRegExp));
-
-// src/rules/base.ts
-var import_ramda5 = require("ramda");
-
-// src/utilities/list.ts
-var import_ramda3 = require("ramda");
-var lenLte = (len) => (0, import_ramda3.compose)((0, import_ramda3.curry)((0, import_ramda3.flip)(import_ramda3.lte))(len), import_ramda3.length);
-var allEqual = (0, import_ramda3.compose)(lenLte(1), import_ramda3.uniq);
-var lengthNonZero = (0, import_ramda3.compose)(Boolean, import_ramda3.length);
-
-// src/utilities/string.ts
-var import_ramda4 = require("ramda");
-var charAt = (0, import_ramda4.invoker)(1, "charAt");
-var notAlpha = (0, import_ramda4.compose)(allEqual, (0, import_ramda4.juxt)([import_ramda4.toLower, import_ramda4.toUpper]));
-var hasAlpha = (0, import_ramda4.compose)(import_ramda4.not, notAlpha);
-var startsWithLower = (0, import_ramda4.allPass)([
-  (0, import_ramda4.compose)((0, import_ramda4.compose)(import_ramda4.not, (0, import_ramda4.match)(/\n/)), charAt(0)),
-  (0, import_ramda4.compose)((0, import_ramda4.compose)(import_ramda4.not, notAlpha), charAt(0)),
-  (0, import_ramda4.compose)(allEqual, (0, import_ramda4.juxt)([import_ramda4.identity, import_ramda4.toLower]), charAt(0))
-]);
-var isUpper = (0, import_ramda4.compose)(allEqual, (0, import_ramda4.juxt)([import_ramda4.toUpper, import_ramda4.identity]));
-
-// src/rules/base.ts
-var isSpaceSuffix = (0, import_ramda5.compose)(lengthNonZero, spaceSuffix);
-var isSpacePrefix = (0, import_ramda5.compose)(lengthNonZero, spacePrefix);
-var spaceBothSides = (0, import_ramda5.compose)(
-  (0, import_ramda5.all)(Boolean),
-  (0, import_ramda5.zipWith)(import_ramda5.call, [isSpaceSuffix, isSpacePrefix]),
-  (0, import_ramda5.map)(words)
-);
-var rightLacksSpacePrefix = (0, import_ramda5.compose)(
-  (0, import_ramda5.all)(Boolean),
-  (0, import_ramda5.zipWith)(import_ramda5.call, [(0, import_ramda5.always)(true), (0, import_ramda5.compose)(import_ramda5.not, isSpacePrefix)]),
-  (0, import_ramda5.map)(words)
-);
-var rightStartsWithLowercase = (0, import_ramda5.compose)(
-  (0, import_ramda5.all)(Boolean),
-  (0, import_ramda5.zipWith)(import_ramda5.call, [(0, import_ramda5.always)(true), (0, import_ramda5.compose)(startsWithLower, fstToken)])
-);
-var rightDelimiterPrefix = (0, import_ramda5.compose)(
-  (0, import_ramda5.all)(Boolean),
-  (0, import_ramda5.zipWith)(import_ramda5.call, [(0, import_ramda5.always)(true), (0, import_ramda5.compose)(lengthNonZero, delimiterPrefix, fstToken)])
-);
-var rightQuotationGenericPrefix = (0, import_ramda5.compose)(
-  (0, import_ramda5.all)(Boolean),
-  (0, import_ramda5.zipWith)(import_ramda5.call, [(0, import_ramda5.always)(true), (0, import_ramda5.compose)(lengthNonZero, quotationGenericPrefix)])
-);
-var rightQuotationClosePrefix = (0, import_ramda5.compose)(
-  (0, import_ramda5.all)(Boolean),
-  (0, import_ramda5.zipWith)(import_ramda5.call, [(0, import_ramda5.always)(true), (0, import_ramda5.compose)(lengthNonZero, quotationClosePrefix, fstToken)])
-);
-var rightBracketsClosePrefix = (0, import_ramda5.compose)(
-  (0, import_ramda5.all)(Boolean),
-  (0, import_ramda5.zipWith)(import_ramda5.call, [(0, import_ramda5.always)(true), (0, import_ramda5.compose)(lengthNonZero, bracketsClosePrefix, fstToken)])
-);
-var rightOnlySpaces = (0, import_ramda5.compose)(
-  (0, import_ramda5.all)(Boolean),
-  (0, import_ramda5.zipWith)(import_ramda5.call, [(0, import_ramda5.always)(true), (0, import_ramda5.compose)(lengthNonZero, spaces)])
-);
-
-// src/rules/initials.ts
-var import_ramda6 = require("ramda");
-var isLeftDotDelimiter = (0, import_ramda6.compose)(lengthNonZero, dotSuffix);
-var isLeftSingleLetter = (0, import_ramda6.compose)((0, import_ramda6.equals)(1), import_ramda6.length, lstWord);
-var isLeftUpper = (0, import_ramda6.compose)(allEqual, (0, import_ramda6.juxt)([import_ramda6.toUpper, import_ramda6.identity]), lstWord);
-var leftHasAlpha = (0, import_ramda6.compose)(hasAlpha, lstWord);
-var isLeftInitials = (0, import_ramda6.allPass)([isLeftDotDelimiter, isLeftSingleLetter, isLeftUpper, leftHasAlpha]);
-var leftInitials = (0, import_ramda6.compose)((0, import_ramda6.all)(Boolean), (0, import_ramda6.zipWith)(import_ramda6.call, [isLeftInitials, (0, import_ramda6.always)(true)]));
-
-// src/rules/abbreviations.ts
-var import_ramda7 = require("ramda");
-
 // src/constants/abbreviations.ts
@@ -444,3 +286,153 @@ var INITIALS = {
 
+// src/lenses/index.ts
+var import_ramda = require("ramda");
+var first = () => (0, import_ramda.lensIndex)(0);
+var second = () => (0, import_ramda.lensIndex)(1);
+var last = () => (0, import_ramda.lensIndex)(-1);
+
+// src/parsers/index.ts
+var firstString = first();
+var fst = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), (0, import_ramda2.view)(firstString));
+var secondString = second();
+var snd = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), (0, import_ramda2.view)(secondString));
+var lastString = last();
+var lst = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), (0, import_ramda2.view)(lastString));
+var sentencePattern = `([^${SENTENCE_END_MARKERS}]*?[${SENTENCE_END_MARKERS}]+)`;
+var senteceFlags = "gmu";
+var sentenceRegExp = new RegExp(sentencePattern, senteceFlags);
+var sentences = (0, import_ramda2.compose)((0, import_ramda2.filter)(Boolean), (0, import_ramda2.split)(sentenceRegExp));
+var sentenceDelimitersPattern = `([${SENTENCE_END_MARKERS}]+)$`;
+var sentenceDelimitersFlags = "gmu";
+var sentenceDelimitersRegExp = new RegExp(sentenceDelimitersPattern, sentenceDelimitersFlags);
+var words = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), (0, import_ramda2.replace)(sentenceDelimitersRegExp)(""));
+var delimiters = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), fst, (0, import_ramda2.match)(sentenceDelimitersRegExp));
+var fstTokenPattern = /^\s*([^\s]+?)(?=\s|$)/;
+var fstTokenFlags = "mu";
+var fstTokenRegExp = new RegExp(fstTokenPattern, fstTokenFlags);
+var fstToken = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), snd, (0, import_ramda2.match)(fstTokenRegExp));
+var fstWord = (0, import_ramda2.compose)(fstToken, words);
+var lstTokenPattern = /([^\s]+)\s*$/;
+var lstTokenFlags = "mu";
+var lstTokenRegExp = new RegExp(lstTokenPattern, lstTokenFlags);
+var lstToken = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), snd, (0, import_ramda2.match)(lstTokenRegExp));
+var nonAlphaStartPattern = /^[^\wа-яА-Я]*/;
+var nonAlphaStartFlags = "gmu";
+var nonAlphaStartRegExp = new RegExp(nonAlphaStartPattern, nonAlphaStartFlags);
+var omitNonAlphaStart = (0, import_ramda2.replace)(nonAlphaStartRegExp, "");
+var lstWord = (0, import_ramda2.compose)(lstToken, words);
+var fstChars = (width = WINDOW_WIDTH) => {
+  const fstCharsPattern = `^[\\s\\S]{0,${width}}`;
+  const fstCharsFlags = "gmu";
+  const fstCharsRegExp = new RegExp(fstCharsPattern, fstCharsFlags);
+  return (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), fst, (0, import_ramda2.match)(fstCharsRegExp));
+};
+var lstChars = (width = WINDOW_WIDTH) => {
+  const lstCharsPattern = `.{0,${width}}$`;
+  const lstCharsFlags = "gmu";
+  const lstCharsRegExp = new RegExp(lstCharsPattern, lstCharsFlags);
+  return (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), fst, (0, import_ramda2.match)(lstCharsRegExp));
+};
+var spacePrefix = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), fst, (0, import_ramda2.match)(/^\s/));
+var spaceSuffix = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), fst, (0, import_ramda2.match)(/\s$/));
+var quotationGenericPrefixPattern = `^([${QUOTATION_GENERIC_MARKERS}]+)`;
+var quotationGenericPrefixFlags = "mu";
+var quotationGenericPrefixRegExp = new RegExp(
+  quotationGenericPrefixPattern,
+  quotationGenericPrefixFlags
+);
+var quotationGenericPrefix = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), snd, (0, import_ramda2.match)(quotationGenericPrefixRegExp));
+var quotationClosePrefixPattern = `^([${QUOTATION_CLOSE_MARKERS}]+)`;
+var quotationClosePrefixFlags = "mu";
+var quotationClosePrefixRegExp = new RegExp(
+  quotationClosePrefixPattern,
+  quotationClosePrefixFlags
+);
+var quotationClosePrefix = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), snd, (0, import_ramda2.match)(quotationClosePrefixRegExp));
+var delimiterPrefixPattern = `^([${SENTENCE_END_MARKERS}]+)`;
+var delimiterPrefixFlags = "mu";
+var delimiterPrefixRegExp = new RegExp(delimiterPrefixPattern, delimiterPrefixFlags);
+var delimiterPrefix = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), snd, (0, import_ramda2.match)(delimiterPrefixRegExp));
+var bracketsClosePrefixPattern = `^([${BRACKETS_CLOSE_MARKERS}]+)`;
+var bracketsClosePrefixFlags = "mu";
+var bracketsClosePrefixRegExp = new RegExp(bracketsClosePrefixPattern, bracketsClosePrefixFlags);
+var bracketsClosePrefix = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), snd, (0, import_ramda2.match)(bracketsClosePrefixRegExp));
+var spacesPattern = /^(\s+)$/;
+var spacesFlags = "gmu";
+var spacesRegExp = new RegExp(spacesPattern, spacesFlags);
+var spaces = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), fst, (0, import_ramda2.match)(spacesRegExp));
+var dotSuffixPattern = /[^.](\.)$/;
+var dotSuffixFlags = "mu";
+var dotSuffixRegExp = new RegExp(dotSuffixPattern, dotSuffixFlags);
+var dotSuffix = (0, import_ramda2.compose)((0, import_ramda2.defaultTo)(""), snd, (0, import_ramda2.match)(dotSuffixRegExp));
+
+// src/rules/base.ts
+var import_ramda5 = require("ramda");
+
+// src/utilities/list.ts
+var import_ramda3 = require("ramda");
+var lenLte = (len) => (0, import_ramda3.compose)((0, import_ramda3.curry)((0, import_ramda3.flip)(import_ramda3.lte))(len), import_ramda3.length);
+var allEqual = (0, import_ramda3.compose)(lenLte(1), import_ramda3.uniq);
+var lengthNonZero = (0, import_ramda3.compose)(Boolean, import_ramda3.length);
+
+// src/utilities/string.ts
+var import_ramda4 = require("ramda");
+var charAt = (0, import_ramda4.invoker)(1, "charAt");
+var notAlpha = (0, import_ramda4.compose)(allEqual, (0, import_ramda4.juxt)([import_ramda4.toLower, import_ramda4.toUpper]));
+var hasAlpha = (0, import_ramda4.compose)(import_ramda4.not, notAlpha);
+var startsWithLower = (0, import_ramda4.allPass)([
+  (0, import_ramda4.compose)(hasAlpha, charAt(0)),
+  (0, import_ramda4.compose)(allEqual, (0, import_ramda4.juxt)([import_ramda4.identity, import_ramda4.toLower]), charAt(0))
+]);
+var startsWithUpper = (0, import_ramda4.allPass)([
+  (0, import_ramda4.compose)(hasAlpha, charAt(0)),
+  (0, import_ramda4.compose)(allEqual, (0, import_ramda4.juxt)([import_ramda4.identity, import_ramda4.toUpper]), charAt(0))
+]);
+var startsWithNewline = (0, import_ramda4.compose)(lengthNonZero, (0, import_ramda4.match)(/^\n/));
+var startsWithHardbreak = (0, import_ramda4.compose)(lengthNonZero, (0, import_ramda4.match)(/^\n\n/));
+var endsWithHardbreak = (0, import_ramda4.compose)(lengthNonZero, (0, import_ramda4.match)(/\n\n$/));
+var isUpper = (0, import_ramda4.compose)(allEqual, (0, import_ramda4.juxt)([import_ramda4.toUpper, import_ramda4.identity]));
+
+// src/rules/base.ts
+var isSpaceSuffix = (0, import_ramda5.compose)(lengthNonZero, spaceSuffix);
+var isSpacePrefix = (0, import_ramda5.compose)(lengthNonZero, spacePrefix);
+var log = (name, action) => {
+  return (...args) => {
+    const result = action(...args);
+    if (process.env.DEBUG) {
+      console.log(name, args, result);
+    }
+    return result;
+  };
+};
+var _ = (0, import_ramda5.always)(true);
+var rule = (name, [left, right], remap = import_ramda5.identity) => {
+  return log(name, (0, import_ramda5.compose)(
+    (0, import_ramda5.all)(Boolean),
+    (0, import_ramda5.zipWith)(import_ramda5.call, [left, right]),
+    (0, import_ramda5.map)(remap)
+  ));
+};
+var spaceBothSides = rule("spaceBothSides", [isSpaceSuffix, isSpacePrefix], words);
+var rightLacksSpacePrefix = rule("rightLacksSpacePrefix", [_, (0, import_ramda5.compose)(import_ramda5.not, isSpacePrefix)], words);
+var rightStartsWithLowercase = rule("rightStartsWithLowercase", [_, (0, import_ramda5.compose)(startsWithLower, fstToken)]);
+var rightDelimiterPrefix = rule("rightDelimiterPrefix", [_, (0, import_ramda5.compose)(lengthNonZero, delimiterPrefix, fstToken)]);
+var rightQuotationGenericPrefix = rule("rightQuotationGenericPrefix", [_, (0, import_ramda5.compose)(lengthNonZero, quotationGenericPrefix)]);
+var rightQuotationClosePrefix = rule("rightQuotationClosePrefix", [_, (0, import_ramda5.compose)(lengthNonZero, quotationClosePrefix, fstToken)]);
+var rightBracketsClosePrefix = rule("rightBracketsClosePrefix", [_, (0, import_ramda5.compose)(lengthNonZero, bracketsClosePrefix, fstToken)]);
+var rightOnlySpaces = rule("rightOnlySpaces", [_, (0, import_ramda5.compose)(lengthNonZero, spaces)]);
+var leftEndsWithHardbreak = rule("leftEndsWithHardbreak", [endsWithHardbreak, _]);
+var rightStartsWithHardbreak = rule("rightStartsWithHardbreak", [_, startsWithHardbreak]);
+var rightStartsNewlineUppercased = rule("rightStartsNewlineUppercased", [_, (0, import_ramda5.allPass)([startsWithNewline, startsWithUpper])]);
+
+// src/rules/initials.ts
+var import_ramda6 = require("ramda");
+var isLeftDotDelimiter = (0, import_ramda6.compose)(lengthNonZero, dotSuffix);
+var isLeftSingleLetter = (0, import_ramda6.compose)((0, import_ramda6.equals)(1), import_ramda6.length, lstWord);
+var isLeftUpper = (0, import_ramda6.compose)(allEqual, (0, import_ramda6.juxt)([import_ramda6.toUpper, import_ramda6.identity]), lstWord);
+var leftHasAlpha = (0, import_ramda6.compose)(hasAlpha, lstWord);
+var isLeftInitials = (0, import_ramda6.allPass)([isLeftDotDelimiter, isLeftSingleLetter, isLeftUpper, leftHasAlpha]);
+var leftInitials = (0, import_ramda6.compose)((0, import_ramda6.all)(Boolean), (0, import_ramda6.zipWith)(import_ramda6.call, [isLeftInitials, (0, import_ramda6.always)(true)]));
+
 // src/rules/abbreviations.ts
+var import_ramda7 = require("ramda");
 var fst2 = (0, import_ramda7.compose)((0, import_ramda7.defaultTo)(""), (0, import_ramda7.view)(first()));
@@ -504,3 +496,3 @@ var snd2 = (0, import_ramda7.compose)((0, import_ramda7.defaultTo)(""), (0, import_ramda7.view)(second()));
 
-// src/sentenize.ts
+// src/index.ts
 var leftPreprocessor = lstChars(20);
@@ -523,24 +515,32 @@ var rightPreprocessor = fstChars(20);
 ]);
+var breakCondition = (0, import_ramda8.anyPass)([
+  leftEndsWithHardbreak,
+  rightStartsWithHardbreak,
+  rightStartsNewlineUppercased
+]);
 var join2 = (0, import_ramda8.compose)(joinCondition, (0, import_ramda8.zipWith)(import_ramda8.call, sidesPreprocessors));
-function processor(text) {
-  const chunks = sentences(text);
-  let left = null;
+var breaks = (0, import_ramda8.compose)(breakCondition, (0, import_ramda8.zipWith)(import_ramda8.call, sidesPreprocessors));
+function sentenize(text) {
+  const parts = text.split(/(\n{2,})/);
   const parsed = [];
-  for (let i = 0; i < chunks.length; i++) {
-    if (!left) {
-      left = chunks[i];
-      continue;
+  for (const part of parts) {
+    const chunks = sentences(part);
+    let left = null;
+    for (const right of chunks) {
+      if (!left) {
+        left = right;
+        continue;
+      }
+      if (!breaks([left, right]) && join2([left, right])) {
+        left += right;
+      } else {
+        parsed.push(left);
+        left = right;
+      }
     }
-    if (join2([left, chunks[i]])) {
-      left += chunks[i];
-    } else {
+    if (left)
       parsed.push(left);
-      left = chunks[i];
-    }
   }
-  if (left)
-    parsed.push(left);
   return parsed;
 }
-var sentenize = processor;
 // Annotate the CommonJS export names for ESM import in node:
@@ -547,0 +547,0 @@ 0 && (module.exports = {

lib/rules/abbreviations.d.ts

 import { Pred } from 'ramda';
-declare const pairAbbreviation: Pred<any[]> | ((obj: string[]) => boolean);
-declare const leftAbbreviation: (obj: string[]) => boolean;
-declare const leftPairsTailAbbreviation: Pred<any[]> | ((obj: string[]) => boolean);
-export { pairAbbreviation, leftAbbreviation, leftPairsTailAbbreviation };
+export declare const pairAbbreviation: Pred<any[]> | ((obj: string[]) => boolean);
+export declare const leftAbbreviation: (obj: string[]) => boolean;
+export declare const leftPairsTailAbbreviation: Pred<any[]> | ((obj: string[]) => boolean);

lib/rules/base.d.ts

@@ -1,9 +0,11 @@
-declare const spaceBothSides: (list: readonly string[]) => boolean;
-declare const rightLacksSpacePrefix: (list: readonly string[]) => boolean;
-declare const rightStartsWithLowercase: (list2: readonly unknown[]) => boolean;
-declare const rightDelimiterPrefix: (list2: readonly unknown[]) => boolean;
-declare const rightQuotationGenericPrefix: (list2: readonly unknown[]) => boolean;
-declare const rightQuotationClosePrefix: (list2: readonly unknown[]) => boolean;
-declare const rightBracketsClosePrefix: (list2: readonly unknown[]) => boolean;
-declare const rightOnlySpaces: (list2: readonly unknown[]) => boolean;
-export { spaceBothSides, rightLacksSpacePrefix, rightStartsWithLowercase, rightDelimiterPrefix, rightQuotationGenericPrefix, rightQuotationClosePrefix, rightBracketsClosePrefix, rightOnlySpaces, };
+export declare const spaceBothSides: (...args: any[]) => any;
+export declare const rightLacksSpacePrefix: (...args: any[]) => any;
+export declare const rightStartsWithLowercase: (...args: any[]) => any;
+export declare const rightDelimiterPrefix: (...args: any[]) => any;
+export declare const rightQuotationGenericPrefix: (...args: any[]) => any;
+export declare const rightQuotationClosePrefix: (...args: any[]) => any;
+export declare const rightBracketsClosePrefix: (...args: any[]) => any;
+export declare const rightOnlySpaces: (...args: any[]) => any;
+export declare const leftEndsWithHardbreak: (...args: any[]) => any;
+export declare const rightStartsWithHardbreak: (...args: any[]) => any;
+export declare const rightStartsNewlineUppercased: (...args: any[]) => any;

lib/rules/index.d.ts

@@ -1,3 +0,3 @@
-export { spaceBothSides, rightLacksSpacePrefix, rightStartsWithLowercase, rightDelimiterPrefix, rightQuotationGenericPrefix, rightQuotationClosePrefix, rightBracketsClosePrefix, rightOnlySpaces, } from './base';
-export { leftInitials } from './initials';
-export { leftAbbreviation, pairAbbreviation, leftPairsTailAbbreviation } from './abbreviations';
+export * from './base';
+export * from './initials';
+export * from './abbreviations';

lib/rules/initials.d.ts

@@ -1,2 +0,1 @@
-declare const leftInitials: (list2: readonly unknown[]) => boolean;
-export { leftInitials };
+export declare const leftInitials: (list2: readonly unknown[]) => boolean;

lib/utilities/index.d.ts

@@ -1,2 +0,2 @@
-export { lenLte, allEqual, lengthNonZero } from './list';
-export { charAt, notAlpha, hasAlpha, startsWithLower, isUpper } from './string';
+export * from './list';
+export * from './string';

lib/utilities/list.d.ts

@@ -1,4 +0,3 @@
-declare const lenLte: (len: number) => (...args: any[][]) => boolean;
-declare const allEqual: (list: readonly unknown[]) => boolean;
-declare const lengthNonZero: (list: any) => boolean;
-export { lenLte, allEqual, lengthNonZero };
+export declare const lenLte: (len: number) => (...args: any[][]) => boolean;
+export declare const allEqual: (list: readonly unknown[]) => boolean;
+export declare const lengthNonZero: (list: any) => boolean;

lib/utilities/string.d.ts

 import { Pred } from 'ramda';
-declare const charAt: (...args: unknown[]) => any;
-declare const notAlpha: (str: string) => boolean;
-declare const hasAlpha: (str: string) => boolean;
-declare const startsWithLower: Pred<any[]>;
-declare const isUpper: (a: string) => boolean;
-export { charAt, notAlpha, hasAlpha, startsWithLower, isUpper };
+export declare const charAt: (...args: unknown[]) => any;
+export declare const notAlpha: (str: string) => boolean;
+export declare const hasAlpha: (str: string) => boolean;
+export declare const startsWithLower: Pred<any[]>;
+export declare const startsWithUpper: Pred<any[]>;
+export declare const startsWithNewline: Pred<any[]>;
+export declare const startsWithHardbreak: Pred<any[]>;
+export declare const endsWithHardbreak: Pred<any[]>;
+export declare const isUpper: (a: string) => boolean;

package.json

 {
   "name": "@diplodoc/sentenizer",
-  "version": "0.0.6",
+  "version": "0.0.7",
   "description": "text segmentation into sentences",
@@ -5,0 +5,0 @@ "homepage": "https://github.com/diplodoc-platform/sentenizer",

New alerts

Environment variable access

Supply chain risk

Package accesses environment variables, which may be a sign of credential stuffing or data theft.

Found 1 instance in 1 package

Worsened metrics

Total package byte prevSize

30359

decreased by-1.68%

Number of package files

18

decreased by-10%

Lines of code

640

decreased by-0.93%

Number of low supply chain risk alerts

2

increased by100%

No dependency changes