@diplodoc/sentenizer - npm Package Compare versions

Comparing version 0.0.7 to 0.0.8

lib/index.js

@@ -5,5 +5,5 @@ var __defProp = Object.defineProperty;
 var __hasOwnProp = Object.prototype.hasOwnProperty;
-var __export = (target, all3) => {
-  for (var name in all3)
-    __defProp(target, name, { get: all3[name], enumerable: true });
+var __export = (target, all2) => {
+  for (var name in all2)
+    __defProp(target, name, { get: all2[name], enumerable: true });
 };
@@ -26,3 +26,3 @@ var __copyProps = (to, from, except, desc) => {
 module.exports = __toCommonJS(src_exports);
-var import_ramda8 = require("ramda");
+var import_ramda7 = require("ramda");
 
@@ -184,4 +184,6 @@ // src/parsers/index.ts
   // гос. экзамены
-  "\u043E\u0442\u043C": true
+  "\u043E\u0442\u043C": true,
   // от отм. 0.000
+  "\u0434\u043E\u0431": true
+  // доб. 1243 (телефон)
 };
@@ -396,2 +398,6 @@ var TAIL = {
 // src/rules/base.ts
+var isLeftDotDelimiter = (0, import_ramda5.compose)(lengthNonZero, dotSuffix);
+var isLeftSingleLetter = (0, import_ramda5.compose)((0, import_ramda5.equals)(1), import_ramda5.length, lstWord);
+var isLeftUpper = (0, import_ramda5.compose)(allEqual, (0, import_ramda5.juxt)([import_ramda5.toUpper, import_ramda5.identity]), lstWord);
+var leftHasAlpha = (0, import_ramda5.compose)(hasAlpha, lstWord);
 var isSpaceSuffix = (0, import_ramda5.compose)(lengthNonZero, spaceSuffix);
@@ -427,62 +433,55 @@ var isSpacePrefix = (0, import_ramda5.compose)(lengthNonZero, spacePrefix);
 var rightStartsNewlineUppercased = rule("rightStartsNewlineUppercased", [_, (0, import_ramda5.allPass)([startsWithNewline, startsWithUpper])]);
+var leftInitials = rule("leftInitials", [(0, import_ramda5.allPass)([isLeftDotDelimiter, isLeftSingleLetter, isLeftUpper, leftHasAlpha]), _]);
 
-// src/rules/initials.ts
+// src/rules/abbreviations.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()));
-var snd2 = (0, import_ramda7.compose)((0, import_ramda7.defaultTo)(""), (0, import_ramda7.view)(second()));
-var isDotDelimiter = (0, import_ramda7.compose)(lengthNonZero, dotSuffix);
-var hash = (0, import_ramda7.compose)(import_ramda7.toLower, (0, import_ramda7.join)("."));
-var insidePairAbbreviationMap = (0, import_ramda7.anyPass)([
-  (0, import_ramda7.prop)(import_ramda7.__, HEAD_PAIR),
-  (0, import_ramda7.prop)(import_ramda7.__, TAIL_PAIR),
-  (0, import_ramda7.prop)(import_ramda7.__, OTHER_PAIR)
+var fst2 = (0, import_ramda6.compose)((0, import_ramda6.defaultTo)(""), (0, import_ramda6.view)(first()));
+var snd2 = (0, import_ramda6.compose)((0, import_ramda6.defaultTo)(""), (0, import_ramda6.view)(second()));
+var isDotDelimiter = (0, import_ramda6.compose)(lengthNonZero, dotSuffix);
+var hash = (0, import_ramda6.compose)(import_ramda6.toLower, (0, import_ramda6.join)("."));
+var insidePairAbbreviationMap = (0, import_ramda6.anyPass)([
+  (0, import_ramda6.prop)(import_ramda6.__, HEAD_PAIR),
+  (0, import_ramda6.prop)(import_ramda6.__, TAIL_PAIR),
+  (0, import_ramda6.prop)(import_ramda6.__, OTHER_PAIR)
 ]);
-var isPairAbbreviation = (0, import_ramda7.compose)(
+var isPairAbbreviation = (0, import_ramda6.compose)(
   insidePairAbbreviationMap,
   hash,
-  (0, import_ramda7.zipWith)(import_ramda7.call, [
-    (0, import_ramda7.compose)(omitNonAlphaStart, lstWord, lstToken),
-    (0, import_ramda7.compose)(fstWord, fstToken)
+  (0, import_ramda6.zipWith)(import_ramda6.call, [
+    (0, import_ramda6.compose)(omitNonAlphaStart, lstWord, lstToken),
+    (0, import_ramda6.compose)(fstWord, fstToken)
   ])
 );
-var pairAbbreviation = (0, import_ramda7.allPass)([
-  (0, import_ramda7.compose)(isDotDelimiter, lstToken, fst2),
+var pairAbbreviation = (0, import_ramda6.allPass)([
+  (0, import_ramda6.compose)(isDotDelimiter, lstToken, fst2),
   isPairAbbreviation
 ]);
-var insideAbbreviationMap = (0, import_ramda7.anyPass)([
+var insideAbbreviationMap = (0, import_ramda6.anyPass)([
   // @ts-ignore
-  (0, import_ramda7.prop)(import_ramda7.__, INITIALS),
+  (0, import_ramda6.prop)(import_ramda6.__, INITIALS),
   // @ts-ignore
-  (0, import_ramda7.prop)(import_ramda7.__, HEAD),
+  (0, import_ramda6.prop)(import_ramda6.__, HEAD),
   // @ts-ignore
-  (0, import_ramda7.prop)(import_ramda7.__, TAIL),
+  (0, import_ramda6.prop)(import_ramda6.__, TAIL),
   // @ts-ignore
-  (0, import_ramda7.prop)(import_ramda7.__, OTHER)
+  (0, import_ramda6.prop)(import_ramda6.__, OTHER)
 ]);
-var isLeftAbbreviation = (0, import_ramda7.compose)(
+var isLeftAbbreviation = (0, import_ramda6.compose)(
   insideAbbreviationMap,
   omitNonAlphaStart,
-  import_ramda7.toLower,
+  import_ramda6.toLower,
   lstWord,
   lstToken
 );
-var leftAbbreviation = (0, import_ramda7.compose)(
-  (0, import_ramda7.allPass)([(0, import_ramda7.compose)(isDotDelimiter, lstToken), isLeftAbbreviation]),
+var leftAbbreviation = (0, import_ramda6.compose)(
+  (0, import_ramda6.allPass)([(0, import_ramda6.compose)(isDotDelimiter, lstToken), isLeftAbbreviation]),
   fst2
 );
-var rightLowercaseOrCaps = (0, import_ramda7.compose)((0, import_ramda7.anyPass)([startsWithLower, isUpper]), fstWord, snd2);
+var isCaps = (0, import_ramda6.allPass)([isUpper, (0, import_ramda6.compose)((0, import_ramda6.lt)(1), import_ramda6.length)]);
+var rightLowercaseOrCaps = (0, import_ramda6.compose)((0, import_ramda6.anyPass)([startsWithLower, isCaps]), fstWord, snd2);
 var before = (s) => (t) => s.slice(0, Math.max(s.indexOf(t), 0));
 var isLeftPairsTail = (left) => {
   const rest = before(left);
-  const head = (0, import_ramda7.compose)(words, lstWord, rest, lstWord, lstToken);
-  return (0, import_ramda7.or)(
+  const head = (0, import_ramda6.compose)(words, lstWord, rest, lstWord, lstToken);
+  return (0, import_ramda6.or)(
     isPairAbbreviation([head(left), lstWord(left)]),
@@ -492,5 +491,5 @@ isPairAbbreviation(lstWord(left).split("."))
 };
-var leftPairsTailAbbreviation = (0, import_ramda7.allPass)([
-  (0, import_ramda7.compose)(isDotDelimiter, lstToken, fst2),
-  (0, import_ramda7.compose)(isLeftPairsTail, fst2),
+var leftPairsTailAbbreviation = (0, import_ramda6.allPass)([
+  (0, import_ramda6.compose)(isDotDelimiter, lstToken, fst2),
+  (0, import_ramda6.compose)(isLeftPairsTail, fst2),
   rightLowercaseOrCaps
@@ -503,3 +502,3 @@ ]);
 var sidesPreprocessors = [leftPreprocessor, rightPreprocessor];
-var joinCondition = (0, import_ramda8.anyPass)([
+var joinCondition = (0, import_ramda7.anyPass)([
   spaceBothSides,
@@ -518,3 +517,3 @@ rightLacksSpacePrefix,
 ]);
-var breakCondition = (0, import_ramda8.anyPass)([
+var breakCondition = (0, import_ramda7.anyPass)([
   leftEndsWithHardbreak,
@@ -524,6 +523,6 @@ rightStartsWithHardbreak,
 ]);
-var join2 = (0, import_ramda8.compose)(joinCondition, (0, import_ramda8.zipWith)(import_ramda8.call, sidesPreprocessors));
-var breaks = (0, import_ramda8.compose)(breakCondition, (0, import_ramda8.zipWith)(import_ramda8.call, sidesPreprocessors));
+var join2 = (0, import_ramda7.compose)(joinCondition, (0, import_ramda7.zipWith)(import_ramda7.call, sidesPreprocessors));
+var breaks = (0, import_ramda7.compose)(breakCondition, (0, import_ramda7.zipWith)(import_ramda7.call, sidesPreprocessors));
 function sentenize(text) {
-  const parts = text.split(/(\n{2,})/);
+  const parts = text.split(/((?:\n\s*){2,})/);
   const parsed = [];
@@ -530,0 +529,0 @@ for (const part of parts) {

lib/rules/base.d.ts

@@ -12,1 +12,2 @@ export declare const spaceBothSides: (...args: any[]) => any;
 export declare const rightStartsNewlineUppercased: (...args: any[]) => any;
+export declare const leftInitials: (...args: any[]) => any;

lib/rules/index.d.ts

 export * from './base';
-export * from './initials';
 export * from './abbreviations';

package.json

 {
   "name": "@diplodoc/sentenizer",
-  "version": "0.0.7",
+  "version": "0.0.8",
   "description": "text segmentation into sentences",
@@ -5,0 +5,0 @@ "homepage": "https://github.com/diplodoc-platform/sentenizer",

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Worsened metrics

Total package byte prevSize

30297

decreased by-0.2%

Number of package files

17

decreased by-5.56%

Lines of code

639

decreased by-0.16%

No dependency changes