axyseo 2.0.0-alpha.1

package/build/languageProcessing/languages/de/helpers/internal/stem.js

@@ -0,0 +1,222 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = stem;
+/**
+ * @file German stemming algorithm. Adapted from:
+ * @author: Joder Illi
+ * @copyright (c) 2010, FormBlitz AG
+ * All rights reserved.
+ * Implementation of the stemming algorithm from http://snowball.tartarus.org/algorithms/german/stemmer.html
+ * Copyright of the algorithm is: Copyright (c) 2001, Dr Martin Porter and can be found at http://snowball.tartarus.org/license.php
+ *
+ * Redistribution and use in source and binary forms, with or without modification, is covered by the standard BSD license.
+ */
+/**
+ * Determines the start index of the R1 region.
+ * R1 is the region after the first non-vowel following a vowel. It should include at least 3 letters.
+ *
+ * @param {string} word The word for which to determine the R1 region.
+ * @returns {number} The start index of the R1 region.
+ */
+const determineR1 = function (word) {
+  // Start with matching first vowel and non-vowel.
+  let r1Index = word.search(/[aeiouyäöü][^aeiouyäöü]/);
+  // Then add 2 since the R1 index is the index after the first vowel & non-vowel matched with the regex.
+  if (r1Index !== -1) {
+    r1Index += 2;
+  }
+
+  // Adjust R1 so that the region preceding it includes at least 3 letters.
+  if (r1Index !== -1 && r1Index < 3) {
+    r1Index = 3;
+  }
+  return r1Index;
+};
+
+/**
+ * Search for the longest among the following suffixes,
+ * (a) em   ern   er
+ * (b) e   en   es
+ * (c) s (preceded by a valid s-ending)
+ * Define a valid s-ending as one of b, d, f, g, h, k, l, m, n, r or t.
+ *
+ * @param {string} word The word to check for the suffix.
+ * @returns {{index1: number, optionUsed1: string}} The index of the suffix and the kind of suffix used.
+ */
+const findSuffixStep1 = function (word) {
+  const a1Index = word.search(/(em|ern|er)$/g);
+  const b1Index = word.search(/(e|en|es)$/g);
+  let c1Index = word.search(/([bdfghklmnrt]s)$/g);
+  // Exclude the s-ending before the s.
+  if (c1Index !== -1) {
+    c1Index++;
+  }
+  let optionUsed1 = "";
+  let index1 = 10000;
+  if (a1Index !== -1) {
+    optionUsed1 = "a";
+    index1 = a1Index;
+    return {
+      index1,
+      optionUsed1
+    };
+  } else if (b1Index !== -1) {
+    optionUsed1 = "b";
+    index1 = b1Index;
+    return {
+      index1,
+      optionUsed1
+    };
+  } else if (c1Index !== -1) {
+    optionUsed1 = "c";
+    index1 = c1Index;
+    return {
+      index1,
+      optionUsed1
+    };
+  }
+  return {
+    index1,
+    optionUsed1
+  };
+};
+
+/**
+ * Search for the longest among the following suffixes,
+ * (a) en   er   est
+ * (b) st (preceded by a valid st-ending, itself preceded by at least 3 letters)
+ * Define a valid st-ending as one of b, d, f, g, h, k, l, m, n or t.
+ *
+ * @param {string} word The word to check for the suffix.
+ * @returns {number} The index of the suffix.
+ */
+const findSuffixStep2 = function (word) {
+  const a2Index = word.search(/(en|er|est)$/g);
+  let b2Index = word.search(/(.{3}[bdfghklmnt]st)$/g);
+  // Exclude the st-ending and the preceding 3 letters.
+  if (b2Index !== -1) {
+    b2Index += 4;
+  }
+  let index2 = 10000;
+  if (a2Index !== -1) {
+    index2 = a2Index;
+  } else if (b2Index !== -1) {
+    index2 = b2Index;
+  }
+  return index2;
+};
+
+/**
+ * Delete the suffix found in step 1 if in R1. (The letter of the valid s-ending is not necessarily in R1.)
+ * If an ending of group (b) is deleted, and the ending is preceded by niss, delete the final s.
+ * (For example, äckern -> äck, ackers -> acker, armes -> arm, bedürfnissen -> bedürfnis).
+ *
+ * @param {string} word         The word for which to delete the suffix.
+ * @param {number} index1       The index of the suffix found in step 1.
+ * @param {string} optionUsed1  The type of the suffix found in step 1.
+ * @param {number} r1Index      The R1 index.
+ *
+ * @returns {string} The word with the deleted suffix.
+ */
+const deleteSuffix1 = function (word, index1, optionUsed1, r1Index) {
+  if (index1 !== 10000 && r1Index !== -1) {
+    if (index1 >= r1Index) {
+      word = word.substring(0, index1);
+      if (optionUsed1 === "b") {
+        if (word.search(/niss$/) !== -1) {
+          word = word.substring(0, word.length - 1);
+        }
+      }
+    }
+  }
+  return word;
+};
+
+/**
+ * Delete the suffix found in step 2 if in R1.
+ * (For example, derbsten -> derbst by step 1, and derbst -> derb by step 2,
+ * since b is a valid st-ending, and is preceded by just 3 letters).
+ *
+ * @param {string} word     The word for which to delete the suffix.
+ * @param {number} index2   The index of the suffix found in step 2.
+ * @param {number} r1Index  The R1 index.
+ *
+ * @returns {string} The word with the deleted suffix.
+ */
+const deleteSuffix2 = function (word, index2, r1Index) {
+  if (index2 !== 10000 && r1Index !== -1) {
+    if (index2 >= r1Index) {
+      word = word.substring(0, index2);
+    }
+  }
+  return word;
+};
+
+/**
+ * Stems irregular verbs.
+ *
+ * @param {Object} morphologyDataVerbs  The German morphology data for verbs.
+ * @param {string} word                 The word to stem.
+ *
+ * @returns {string} The stemmed word.
+ */
+const stemIrregularVerbs = function (morphologyDataVerbs, word) {
+  const irregularVerbs = morphologyDataVerbs.veryIrregularVerbs;
+  const matchedParadigm = irregularVerbs.find(paradigm => {
+    const forms = paradigm.forms;
+    return forms.includes(word);
+  });
+  if (matchedParadigm) {
+    return matchedParadigm.stem;
+  }
+  return null;
+};
+
+/**
+ * Stems German words.
+ *
+ * @param {Object} morphologyDataVerbs  The German morphology data for verbs.
+ * @param {string} word                 The word to stem.
+ *
+ * @returns {string} The stemmed word.
+ */
+function stem(morphologyDataVerbs, word) {
+  // Check if word is a very irregular verb, and if so, return its stem.
+  const veryIrregularVerbStem = stemIrregularVerbs(morphologyDataVerbs, word);
+  if (veryIrregularVerbStem) {
+    return veryIrregularVerbStem;
+  }
+
+  // Put u and y between vowels into upper case.
+  word = word.replace(/([aeiouyäöü])u([aeiouyäöü])/g, "$1U$2");
+  word = word.replace(/([aeiouyäöü])y([aeiouyäöü])/g, "$1Y$2");
+  word = word.replace(/([aeiouyäöü])i([aeiouyäöü])/g, "$1I$2");
+  word = word.replace(/([aeiouyäöü])e([aeiouyäöü])/g, "$1E$2");
+
+  // Find the start index of the R1 region.
+  const r1Index = determineR1(word);
+
+  // Find suffixes as defined in step 1.
+  const index1 = findSuffixStep1(word).index1;
+  const optionUsed1 = findSuffixStep1(word).optionUsed1;
+
+  // Delete the suffix found in step 1.
+  word = deleteSuffix1(word, index1, optionUsed1, r1Index);
+
+  // Find suffixes as defined in step 2.
+  const index2 = findSuffixStep2(word);
+
+  // Delete the suffix found in step 2.
+  word = deleteSuffix2(word, index2, r1Index);
+
+  // Turn U and Y back into lower case.
+  word = word.replace(/U/g, "u");
+  word = word.replace(/Y/g, "y");
+  word = word.replace(/I/g, "i");
+  word = word.replace(/E/g, "e");
+  return word;
+}
+//# sourceMappingURL=stem.js.map

package/build/languageProcessing/languages/de/helpers/internal/stem.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"stem.js","names":["determineR1","word","r1Index","search","findSuffixStep1","a1Index","b1Index","c1Index","optionUsed1","index1","findSuffixStep2","a2Index","b2Index","index2","deleteSuffix1","substring","length","deleteSuffix2","stemIrregularVerbs","morphologyDataVerbs","irregularVerbs","veryIrregularVerbs","matchedParadigm","find","paradigm","forms","includes","stem","veryIrregularVerbStem","replace"],"sources":["../../../../../../src/languageProcessing/languages/de/helpers/internal/stem.js"],"sourcesContent":["/**\n * @file German stemming algorithm. Adapted from:\n * @author: Joder Illi\n * @copyright (c) 2010, FormBlitz AG\n * All rights reserved.\n * Implementation of the stemming algorithm from http://snowball.tartarus.org/algorithms/german/stemmer.html\n * Copyright of the algorithm is: Copyright (c) 2001, Dr Martin Porter and can be found at http://snowball.tartarus.org/license.php\n *\n * Redistribution and use in source and binary forms, with or without modification, is covered by the standard BSD license.\n */\n/**\n * Determines the start index of the R1 region.\n * R1 is the region after the first non-vowel following a vowel. It should include at least 3 letters.\n *\n * @param {string} word The word for which to determine the R1 region.\n * @returns {number} The start index of the R1 region.\n */\nconst determineR1 = function( word ) {\n\t// Start with matching first vowel and non-vowel.\n\tlet r1Index = word.search( /[aeiouyäöü][^aeiouyäöü]/ );\n\t// Then add 2 since the R1 index is the index after the first vowel & non-vowel matched with the regex.\n\tif ( r1Index !== -1 ) {\n\t\tr1Index += 2;\n\t}\n\n\t// Adjust R1 so that the region preceding it includes at least 3 letters.\n\tif ( r1Index !== -1 && r1Index < 3 ) {\n\t\tr1Index = 3;\n\t}\n\n\treturn r1Index;\n};\n\n/**\n * Search for the longest among the following suffixes,\n * (a) em   ern   er\n * (b) e   en   es\n * (c) s (preceded by a valid s-ending)\n * Define a valid s-ending as one of b, d, f, g, h, k, l, m, n, r or t.\n *\n * @param {string} word The word to check for the suffix.\n * @returns {{index1: number, optionUsed1: string}} The index of the suffix and the kind of suffix used.\n */\nconst findSuffixStep1 = function( word ) {\n\tconst a1Index = word.search( /(em|ern|er)$/g );\n\tconst b1Index = word.search( /(e|en|es)$/g );\n\tlet c1Index = word.search( /([bdfghklmnrt]s)$/g );\n\t// Exclude the s-ending before the s.\n\tif ( c1Index !== -1 ) {\n\t\tc1Index++;\n\t}\n\tlet optionUsed1 = \"\";\n\tlet index1 = 10000;\n\tif ( a1Index !== -1 ) {\n\t\toptionUsed1 = \"a\";\n\t\tindex1 = a1Index;\n\n\t\treturn { index1, optionUsed1 };\n\t} else if ( b1Index !== -1 ) {\n\t\toptionUsed1 = \"b\";\n\t\tindex1 = b1Index;\n\n\t\treturn { index1, optionUsed1 };\n\t} else if ( c1Index !== -1 ) {\n\t\toptionUsed1 = \"c\";\n\t\tindex1 = c1Index;\n\n\t\treturn { index1, optionUsed1 };\n\t}\n\n\treturn { index1, optionUsed1 };\n};\n\n/**\n * Search for the longest among the following suffixes,\n * (a) en   er   est\n * (b) st (preceded by a valid st-ending, itself preceded by at least 3 letters)\n * Define a valid st-ending as one of b, d, f, g, h, k, l, m, n or t.\n *\n * @param {string} word The word to check for the suffix.\n * @returns {number} The index of the suffix.\n */\nconst findSuffixStep2 = function( word ) {\n\tconst a2Index = word.search( /(en|er|est)$/g );\n\tlet b2Index = word.search( /(.{3}[bdfghklmnt]st)$/g );\n\t// Exclude the st-ending and the preceding 3 letters.\n\tif ( b2Index !== -1 ) {\n\t\tb2Index += 4;\n\t}\n\tlet index2 = 10000;\n\tif ( a2Index !== -1 ) {\n\t\tindex2 = a2Index;\n\t} else if ( b2Index !== -1  ) {\n\t\tindex2 = b2Index;\n\t}\n\n\treturn index2;\n};\n\n/**\n * Delete the suffix found in step 1 if in R1. (The letter of the valid s-ending is not necessarily in R1.)\n * If an ending of group (b) is deleted, and the ending is preceded by niss, delete the final s.\n * (For example, äckern -> äck, ackers -> acker, armes -> arm, bedürfnissen -> bedürfnis).\n *\n * @param {string} word         The word for which to delete the suffix.\n * @param {number} index1       The index of the suffix found in step 1.\n * @param {string} optionUsed1  The type of the suffix found in step 1.\n * @param {number} r1Index      The R1 index.\n *\n * @returns {string} The word with the deleted suffix.\n */\nconst deleteSuffix1 = function( word, index1, optionUsed1, r1Index ) {\n\tif ( index1 !== 10000 && r1Index !== -1 ) {\n\t\tif ( index1 >= r1Index ) {\n\t\t\tword = word.substring( 0, index1 );\n\t\t\tif ( optionUsed1 === \"b\" ) {\n\t\t\t\tif ( word.search( /niss$/ ) !== -1 ) {\n\t\t\t\t\tword = word.substring( 0, word.length - 1 );\n\t\t\t\t}\n\t\t\t}\n\t\t}\n\t}\n\treturn word;\n};\n\n/**\n * Delete the suffix found in step 2 if in R1.\n * (For example, derbsten -> derbst by step 1, and derbst -> derb by step 2,\n * since b is a valid st-ending, and is preceded by just 3 letters).\n *\n * @param {string} word     The word for which to delete the suffix.\n * @param {number} index2   The index of the suffix found in step 2.\n * @param {number} r1Index  The R1 index.\n *\n * @returns {string} The word with the deleted suffix.\n */\nconst deleteSuffix2 = function( word, index2, r1Index ) {\n\tif ( index2 !== 10000 && r1Index !== -1 ) {\n\t\tif ( index2 >= r1Index ) {\n\t\t\tword = word.substring( 0, index2 );\n\t\t}\n\t}\n\treturn word;\n};\n\n\n/**\n * Stems irregular verbs.\n *\n * @param {Object} morphologyDataVerbs  The German morphology data for verbs.\n * @param {string} word                 The word to stem.\n *\n * @returns {string} The stemmed word.\n */\nconst stemIrregularVerbs = function( morphologyDataVerbs, word ) {\n\tconst irregularVerbs = morphologyDataVerbs.veryIrregularVerbs;\n\n\tconst matchedParadigm = irregularVerbs.find( paradigm => {\n\t\tconst forms = paradigm.forms;\n\t\treturn forms.includes( word );\n\t} );\n\n\tif ( matchedParadigm ) {\n\t\treturn matchedParadigm.stem;\n\t}\n\n\treturn null;\n};\n\n/**\n * Stems German words.\n *\n * @param {Object} morphologyDataVerbs  The German morphology data for verbs.\n * @param {string} word                 The word to stem.\n *\n * @returns {string} The stemmed word.\n */\nexport default function stem( morphologyDataVerbs, word ) {\n\t// Check if word is a very irregular verb, and if so, return its stem.\n\tconst veryIrregularVerbStem = stemIrregularVerbs( morphologyDataVerbs, word );\n\n\tif ( veryIrregularVerbStem ) {\n\t\treturn veryIrregularVerbStem;\n\t}\n\n\t// Put u and y between vowels into upper case.\n\tword = word.replace( /([aeiouyäöü])u([aeiouyäöü])/g, \"$1U$2\" );\n\tword = word.replace( /([aeiouyäöü])y([aeiouyäöü])/g, \"$1Y$2\" );\n\tword = word.replace( /([aeiouyäöü])i([aeiouyäöü])/g, \"$1I$2\" );\n\tword = word.replace( /([aeiouyäöü])e([aeiouyäöü])/g, \"$1E$2\" );\n\n\t// Find the start index of the R1 region.\n\tconst r1Index = determineR1( word );\n\n\t// Find suffixes as defined in step 1.\n\tconst index1 = findSuffixStep1( word ).index1;\n\tconst optionUsed1 = findSuffixStep1( word ).optionUsed1;\n\n\t// Delete the suffix found in step 1.\n\tword = deleteSuffix1( word, index1, optionUsed1, r1Index );\n\n\t// Find suffixes as defined in step 2.\n\tconst index2 = findSuffixStep2( word );\n\n\t// Delete the suffix found in step 2.\n\tword = deleteSuffix2( word, index2, r1Index );\n\n\t// Turn U and Y back into lower case.\n\tword = word.replace( /U/g, \"u\" );\n\tword = word.replace( /Y/g, \"y\" );\n\tword = word.replace( /I/g, \"i\" );\n\tword = word.replace( /E/g, \"e\" );\n\n\treturn word;\n}\n"],"mappings":";;;;;;AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMA,WAAW,GAAG,SAAAA,CAAUC,IAAI,EAAG;EACpC;EACA,IAAIC,OAAO,GAAGD,IAAI,CAACE,MAAM,CAAE,yBAA0B,CAAC;EACtD;EACA,IAAKD,OAAO,KAAK,CAAC,CAAC,EAAG;IACrBA,OAAO,IAAI,CAAC;EACb;;EAEA;EACA,IAAKA,OAAO,KAAK,CAAC,CAAC,IAAIA,OAAO,GAAG,CAAC,EAAG;IACpCA,OAAO,GAAG,CAAC;EACZ;EAEA,OAAOA,OAAO;AACf,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,eAAe,GAAG,SAAAA,CAAUH,IAAI,EAAG;EACxC,MAAMI,OAAO,GAAGJ,IAAI,CAACE,MAAM,CAAE,eAAgB,CAAC;EAC9C,MAAMG,OAAO,GAAGL,IAAI,CAACE,MAAM,CAAE,aAAc,CAAC;EAC5C,IAAII,OAAO,GAAGN,IAAI,CAACE,MAAM,CAAE,oBAAqB,CAAC;EACjD;EACA,IAAKI,OAAO,KAAK,CAAC,CAAC,EAAG;IACrBA,OAAO,EAAE;EACV;EACA,IAAIC,WAAW,GAAG,EAAE;EACpB,IAAIC,MAAM,GAAG,KAAK;EAClB,IAAKJ,OAAO,KAAK,CAAC,CAAC,EAAG;IACrBG,WAAW,GAAG,GAAG;IACjBC,MAAM,GAAGJ,OAAO;IAEhB,OAAO;MAAEI,MAAM;MAAED;IAAY,CAAC;EAC/B,CAAC,MAAM,IAAKF,OAAO,KAAK,CAAC,CAAC,EAAG;IAC5BE,WAAW,GAAG,GAAG;IACjBC,MAAM,GAAGH,OAAO;IAEhB,OAAO;MAAEG,MAAM;MAAED;IAAY,CAAC;EAC/B,CAAC,MAAM,IAAKD,OAAO,KAAK,CAAC,CAAC,EAAG;IAC5BC,WAAW,GAAG,GAAG;IACjBC,MAAM,GAAGF,OAAO;IAEhB,OAAO;MAAEE,MAAM;MAAED;IAAY,CAAC;EAC/B;EAEA,OAAO;IAAEC,MAAM;IAAED;EAAY,CAAC;AAC/B,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,eAAe,GAAG,SAAAA,CAAUT,IAAI,EAAG;EACxC,MAAMU,OAAO,GAAGV,IAAI,CAACE,MAAM,CAAE,eAAgB,CAAC;EAC9C,IAAIS,OAAO,GAAGX,IAAI,CAACE,MAAM,CAAE,wBAAyB,CAAC;EACrD;EACA,IAAKS,OAAO,KAAK,CAAC,CAAC,EAAG;IACrBA,OAAO,IAAI,CAAC;EACb;EACA,IAAIC,MAAM,GAAG,KAAK;EAClB,IAAKF,OAAO,KAAK,CAAC,CAAC,EAAG;IACrBE,MAAM,GAAGF,OAAO;EACjB,CAAC,MAAM,IAAKC,OAAO,KAAK,CAAC,CAAC,EAAI;IAC7BC,MAAM,GAAGD,OAAO;EACjB;EAEA,OAAOC,MAAM;AACd,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,aAAa,GAAG,SAAAA,CAAUb,IAAI,EAAEQ,MAAM,EAAED,WAAW,EAAEN,OAAO,EAAG;EACpE,IAAKO,MAAM,KAAK,KAAK,IAAIP,OAAO,KAAK,CAAC,CAAC,EAAG;IACzC,IAAKO,MAAM,IAAIP,OAAO,EAAG;MACxBD,IAAI,GAAGA,IAAI,CAACc,SAAS,CAAE,CAAC,EAAEN,MAAO,CAAC;MAClC,IAAKD,WAAW,KAAK,GAAG,EAAG;QAC1B,IAAKP,IAAI,CAACE,MAAM,CAAE,OAAQ,CAAC,KAAK,CAAC,CAAC,EAAG;UACpCF,IAAI,GAAGA,IAAI,CAACc,SAAS,CAAE,CAAC,EAAEd,IAAI,CAACe,MAAM,GAAG,CAAE,CAAC;QAC5C;MACD;IACD;EACD;EACA,OAAOf,IAAI;AACZ,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMgB,aAAa,GAAG,SAAAA,CAAUhB,IAAI,EAAEY,MAAM,EAAEX,OAAO,EAAG;EACvD,IAAKW,MAAM,KAAK,KAAK,IAAIX,OAAO,KAAK,CAAC,CAAC,EAAG;IACzC,IAAKW,MAAM,IAAIX,OAAO,EAAG;MACxBD,IAAI,GAAGA,IAAI,CAACc,SAAS,CAAE,CAAC,EAAEF,MAAO,CAAC;IACnC;EACD;EACA,OAAOZ,IAAI;AACZ,CAAC;;AAGD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMiB,kBAAkB,GAAG,SAAAA,CAAUC,mBAAmB,EAAElB,IAAI,EAAG;EAChE,MAAMmB,cAAc,GAAGD,mBAAmB,CAACE,kBAAkB;EAE7D,MAAMC,eAAe,GAAGF,cAAc,CAACG,IAAI,CAAEC,QAAQ,IAAI;IACxD,MAAMC,KAAK,GAAGD,QAAQ,CAACC,KAAK;IAC5B,OAAOA,KAAK,CAACC,QAAQ,CAAEzB,IAAK,CAAC;EAC9B,CAAE,CAAC;EAEH,IAAKqB,eAAe,EAAG;IACtB,OAAOA,eAAe,CAACK,IAAI;EAC5B;EAEA,OAAO,IAAI;AACZ,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAASA,IAAIA,CAAER,mBAAmB,EAAElB,IAAI,EAAG;EACzD;EACA,MAAM2B,qBAAqB,GAAGV,kBAAkB,CAAEC,mBAAmB,EAAElB,IAAK,CAAC;EAE7E,IAAK2B,qBAAqB,EAAG;IAC5B,OAAOA,qBAAqB;EAC7B;;EAEA;EACA3B,IAAI,GAAGA,IAAI,CAAC4B,OAAO,CAAE,8BAA8B,EAAE,OAAQ,CAAC;EAC9D5B,IAAI,GAAGA,IAAI,CAAC4B,OAAO,CAAE,8BAA8B,EAAE,OAAQ,CAAC;EAC9D5B,IAAI,GAAGA,IAAI,CAAC4B,OAAO,CAAE,8BAA8B,EAAE,OAAQ,CAAC;EAC9D5B,IAAI,GAAGA,IAAI,CAAC4B,OAAO,CAAE,8BAA8B,EAAE,OAAQ,CAAC;;EAE9D;EACA,MAAM3B,OAAO,GAAGF,WAAW,CAAEC,IAAK,CAAC;;EAEnC;EACA,MAAMQ,MAAM,GAAGL,eAAe,CAAEH,IAAK,CAAC,CAACQ,MAAM;EAC7C,MAAMD,WAAW,GAAGJ,eAAe,CAAEH,IAAK,CAAC,CAACO,WAAW;;EAEvD;EACAP,IAAI,GAAGa,aAAa,CAAEb,IAAI,EAAEQ,MAAM,EAAED,WAAW,EAAEN,OAAQ,CAAC;;EAE1D;EACA,MAAMW,MAAM,GAAGH,eAAe,CAAET,IAAK,CAAC;;EAEtC;EACAA,IAAI,GAAGgB,aAAa,CAAEhB,IAAI,EAAEY,MAAM,EAAEX,OAAQ,CAAC;;EAE7C;EACAD,IAAI,GAAGA,IAAI,CAAC4B,OAAO,CAAE,IAAI,EAAE,GAAI,CAAC;EAChC5B,IAAI,GAAGA,IAAI,CAAC4B,OAAO,CAAE,IAAI,EAAE,GAAI,CAAC;EAChC5B,IAAI,GAAGA,IAAI,CAAC4B,OAAO,CAAE,IAAI,EAAE,GAAI,CAAC;EAChC5B,IAAI,GAAGA,IAAI,CAAC4B,OAAO,CAAE,IAAI,EAAE,GAAI,CAAC;EAEhC,OAAO5B,IAAI;AACZ","ignoreList":[]}

package/build/languageProcessing/languages/de/helpers/memoizedSentenceTokenizer.js

@@ -0,0 +1,37 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _lodash = require("lodash");
+var _SentenceTokenizer = _interopRequireDefault(require("./internal/SentenceTokenizer"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Returns the sentences from a certain text.
+ *
+ * @param {string} text 					The text to retrieve sentences from.
+ * @param {boolean} [trimSentences=true] 	Whether to trim whitespace from the beginning and end of the sentences or not.
+ *
+ * @returns {Array<string>} The list of sentences in the text.
+ */
+function getSentenceTokenizer(text, trimSentences = true) {
+  const sentenceTokenizer = new _SentenceTokenizer.default();
+  const {
+    tokenizer,
+    tokens
+  } = sentenceTokenizer.createTokenizer();
+  sentenceTokenizer.tokenize(tokenizer, text);
+  return tokens.length === 0 ? [] : sentenceTokenizer.getSentencesFromTokens(tokens, trimSentences);
+}
+
+/*
+ * The second argument to the memoize function is a so-called resolver function.
+ * It creates a cache key consisting of a combination of all arguments to a function.
+ * This is needed because by default, only the first argument to a function is used as the map cache key by the memoize function.
+ * This means that a function is only re-run if the value of the first argument changes.
+ * We want to re-run the getSentenceTokenizer function also when only the second argument changes to prevent cache collisions.
+ * @see https://lodash.com/docs/4.17.15#memoize
+ */
+var _default = exports.default = (0, _lodash.memoize)(getSentenceTokenizer, (...args) => JSON.stringify(args));
+//# sourceMappingURL=memoizedSentenceTokenizer.js.map

package/build/languageProcessing/languages/de/helpers/memoizedSentenceTokenizer.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"memoizedSentenceTokenizer.js","names":["_lodash","require","_SentenceTokenizer","_interopRequireDefault","e","__esModule","default","getSentenceTokenizer","text","trimSentences","sentenceTokenizer","SentenceTokenizer","tokenizer","tokens","createTokenizer","tokenize","length","getSentencesFromTokens","_default","exports","memoize","args","JSON","stringify"],"sources":["../../../../../src/languageProcessing/languages/de/helpers/memoizedSentenceTokenizer.js"],"sourcesContent":["import { memoize } from \"lodash\";\nimport SentenceTokenizer from \"./internal/SentenceTokenizer\";\n\n/**\n * Returns the sentences from a certain text.\n *\n * @param {string} text \t\t\t\t\tThe text to retrieve sentences from.\n * @param {boolean} [trimSentences=true] \tWhether to trim whitespace from the beginning and end of the sentences or not.\n *\n * @returns {Array<string>} The list of sentences in the text.\n */\nfunction getSentenceTokenizer( text, trimSentences = true ) {\n\tconst sentenceTokenizer = new SentenceTokenizer();\n\tconst { tokenizer, tokens } = sentenceTokenizer.createTokenizer();\n\tsentenceTokenizer.tokenize( tokenizer, text );\n\n\treturn ( tokens.length === 0 ? [] : sentenceTokenizer.getSentencesFromTokens( tokens, trimSentences ) );\n}\n\n/*\n * The second argument to the memoize function is a so-called resolver function.\n * It creates a cache key consisting of a combination of all arguments to a function.\n * This is needed because by default, only the first argument to a function is used as the map cache key by the memoize function.\n * This means that a function is only re-run if the value of the first argument changes.\n * We want to re-run the getSentenceTokenizer function also when only the second argument changes to prevent cache collisions.\n * @see https://lodash.com/docs/4.17.15#memoize\n */\nexport default memoize( getSentenceTokenizer, ( ...args ) => JSON.stringify( args ) );\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AACA,IAAAC,kBAAA,GAAAC,sBAAA,CAAAF,OAAA;AAA6D,SAAAE,uBAAAC,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAE7D;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASG,oBAAoBA,CAAEC,IAAI,EAAEC,aAAa,GAAG,IAAI,EAAG;EAC3D,MAAMC,iBAAiB,GAAG,IAAIC,0BAAiB,CAAC,CAAC;EACjD,MAAM;IAAEC,SAAS;IAAEC;EAAO,CAAC,GAAGH,iBAAiB,CAACI,eAAe,CAAC,CAAC;EACjEJ,iBAAiB,CAACK,QAAQ,CAAEH,SAAS,EAAEJ,IAAK,CAAC;EAE7C,OAASK,MAAM,CAACG,MAAM,KAAK,CAAC,GAAG,EAAE,GAAGN,iBAAiB,CAACO,sBAAsB,CAAEJ,MAAM,EAAEJ,aAAc,CAAC;AACtG;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AAPA,IAAAS,QAAA,GAAAC,OAAA,CAAAb,OAAA,GAQe,IAAAc,eAAO,EAAEb,oBAAoB,EAAE,CAAE,GAAGc,IAAI,KAAMC,IAAI,CAACC,SAAS,CAAEF,IAAK,CAAE,CAAC","ignoreList":[]}

package/build/languageProcessing/languages/de/values/Clause.js

@@ -0,0 +1,91 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _lodash = require("lodash");
+var _index = require("../../../index");
+var _getParticiples = _interopRequireDefault(require("../helpers/internal/getParticiples"));
+var _exceptionsParticiplesActive = _interopRequireDefault(require("../config/internal/exceptionsParticiplesActive.js"));
+var _passiveVoiceAuxiliaries = require("../config/internal/passiveVoiceAuxiliaries.js");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+const {
+  indices,
+  values
+} = _index.languageProcessing;
+const {
+  getIndicesByWord,
+  getIndicesByWordList
+} = indices;
+const {
+  Clause
+} = values;
+const exceptionsRegex = /\S+(apparat|arbeit|dienst|haft|halt|keit|kraft|not|pflicht|schaft|schrift|tät|wert|zeit)($|[ \n\r\t.,'()"+-;!?:/»«‹›<>])/gi;
+
+/**
+ * Creates a Clause object for the German language.
+ */
+class GermanClause extends Clause {
+  /**
+   * Constructor.
+   *
+   * @param {string} clauseText   The text of the clause.
+   * @param {Array} auxiliaries   The auxiliaries.
+   *
+   * @constructor
+   */
+  constructor(clauseText, auxiliaries) {
+    super(clauseText, auxiliaries);
+    this._participles = (0, _getParticiples.default)(this.getClauseText());
+    this.checkParticiples();
+  }
+
+  /**
+   * Checks if any exceptions are applicable to this participle that would result in the clause not being passive.
+   * If no exceptions are found, the clause is passive.
+   *
+   * @returns {void}
+   */
+  checkParticiples() {
+    const foundParticiples = this.getParticiples().filter(participle => {
+      return !this.hasNounSuffix(participle) && !(0, _lodash.includes)(_exceptionsParticiplesActive.default, participle) && !this.hasHabenSeinException(participle) && !(0, _lodash.includes)(_passiveVoiceAuxiliaries.participleLike, participle);
+    });
+    this.setPassive(foundParticiples.length > 0);
+  }
+
+  /**
+   * Checks whether a found participle ends in a noun suffix.
+   * If a word ends in a noun suffix from the exceptionsRegex, it isn't a participle.
+   *
+   * @param {string} participle   The participle to check.
+   *
+   * @returns {boolean} Returns true if it ends in a noun suffix, otherwise returns false.
+   */
+  hasNounSuffix(participle) {
+    return participle.match(exceptionsRegex) !== null;
+  }
+
+  /**
+   * Checks whether a participle is followed by 'haben' or 'sein'.
+   * If a participle is followed by one of these, the clause is not passive.
+   *
+   * @param {string} participle   The participle to check.
+   *
+   * @returns {boolean} Returns true if it is an exception, otherwise returns false.
+   */
+  hasHabenSeinException(participle) {
+    const participleIndices = getIndicesByWord(participle, this.getClauseText());
+    let habenSeinIndices = getIndicesByWordList(['haben', 'sein'], this.getClauseText());
+
+    // Don't check further if there is no participle or no haben/sein.
+    if (participleIndices.length === 0 || habenSeinIndices.length === 0) {
+      return false;
+    }
+    habenSeinIndices = (0, _lodash.map)(habenSeinIndices, 'index');
+    const currentParticiple = participleIndices[0];
+    return (0, _lodash.includes)(habenSeinIndices, currentParticiple.index + currentParticiple.match.length + 1);
+  }
+}
+var _default = exports.default = GermanClause;
+//# sourceMappingURL=Clause.js.map

package/build/languageProcessing/languages/de/values/Clause.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"Clause.js","names":["_lodash","require","_index","_getParticiples","_interopRequireDefault","_exceptionsParticiplesActive","_passiveVoiceAuxiliaries","e","__esModule","default","indices","values","languageProcessing","getIndicesByWord","getIndicesByWordList","Clause","exceptionsRegex","GermanClause","constructor","clauseText","auxiliaries","_participles","getParticiples","getClauseText","checkParticiples","foundParticiples","filter","participle","hasNounSuffix","includes","exceptionsParticiplesActive","hasHabenSeinException","participleLikeAuxiliaries","setPassive","length","match","participleIndices","habenSeinIndices","map","currentParticiple","index","_default","exports"],"sources":["../../../../../src/languageProcessing/languages/de/values/Clause.js"],"sourcesContent":["import {includes, map} from 'lodash';\nimport {languageProcessing} from '../../../index';\nconst {indices, values} = languageProcessing;\nconst {getIndicesByWord, getIndicesByWordList} = indices;\nconst {Clause} = values;\n\nimport getParticiples from '../helpers/internal/getParticiples';\nimport exceptionsParticiplesActive from '../config/internal/exceptionsParticiplesActive.js';\nimport {participleLike as participleLikeAuxiliaries} from '../config/internal/passiveVoiceAuxiliaries.js';\n\nconst exceptionsRegex = /\\S+(apparat|arbeit|dienst|haft|halt|keit|kraft|not|pflicht|schaft|schrift|tät|wert|zeit)($|[ \\n\\r\\t.,'()\"+-;!?:/»«‹›<>])/gi;\n\n/**\n * Creates a Clause object for the German language.\n */\nclass GermanClause extends Clause {\n  /**\n   * Constructor.\n   *\n   * @param {string} clauseText   The text of the clause.\n   * @param {Array} auxiliaries   The auxiliaries.\n   *\n   * @constructor\n   */\n  constructor(clauseText, auxiliaries) {\n    super(clauseText, auxiliaries);\n    this._participles = getParticiples(this.getClauseText());\n    this.checkParticiples();\n  }\n\n  /**\n   * Checks if any exceptions are applicable to this participle that would result in the clause not being passive.\n   * If no exceptions are found, the clause is passive.\n   *\n   * @returns {void}\n   */\n  checkParticiples() {\n    const foundParticiples = this.getParticiples().filter(participle => {\n      return (\n        !this.hasNounSuffix(participle) &&\n        !includes(exceptionsParticiplesActive, participle) &&\n        !this.hasHabenSeinException(participle) &&\n        !includes(participleLikeAuxiliaries, participle)\n      );\n    });\n\n    this.setPassive(foundParticiples.length > 0);\n  }\n\n  /**\n   * Checks whether a found participle ends in a noun suffix.\n   * If a word ends in a noun suffix from the exceptionsRegex, it isn't a participle.\n   *\n   * @param {string} participle   The participle to check.\n   *\n   * @returns {boolean} Returns true if it ends in a noun suffix, otherwise returns false.\n   */\n  hasNounSuffix(participle) {\n    return participle.match(exceptionsRegex) !== null;\n  }\n\n  /**\n   * Checks whether a participle is followed by 'haben' or 'sein'.\n   * If a participle is followed by one of these, the clause is not passive.\n   *\n   * @param {string} participle   The participle to check.\n   *\n   * @returns {boolean} Returns true if it is an exception, otherwise returns false.\n   */\n  hasHabenSeinException(participle) {\n    const participleIndices = getIndicesByWord(participle, this.getClauseText());\n    let habenSeinIndices = getIndicesByWordList(['haben', 'sein'], this.getClauseText());\n\n    // Don't check further if there is no participle or no haben/sein.\n    if (participleIndices.length === 0 || habenSeinIndices.length === 0) {\n      return false;\n    }\n\n    habenSeinIndices = map(habenSeinIndices, 'index');\n    const currentParticiple = participleIndices[0];\n    return includes(habenSeinIndices, currentParticiple.index + currentParticiple.match.length + 1);\n  }\n}\n\nexport default GermanClause;\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AACA,IAAAC,MAAA,GAAAD,OAAA;AAKA,IAAAE,eAAA,GAAAC,sBAAA,CAAAH,OAAA;AACA,IAAAI,4BAAA,GAAAD,sBAAA,CAAAH,OAAA;AACA,IAAAK,wBAAA,GAAAL,OAAA;AAA0G,SAAAG,uBAAAG,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAN1G,MAAM;EAACG,OAAO;EAAEC;AAAM,CAAC,GAAGC,yBAAkB;AAC5C,MAAM;EAACC,gBAAgB;EAAEC;AAAoB,CAAC,GAAGJ,OAAO;AACxD,MAAM;EAACK;AAAM,CAAC,GAAGJ,MAAM;AAMvB,MAAMK,eAAe,GAAG,4HAA4H;;AAEpJ;AACA;AACA;AACA,MAAMC,YAAY,SAASF,MAAM,CAAC;EAChC;AACF;AACA;AACA;AACA;AACA;AACA;AACA;EACEG,WAAWA,CAACC,UAAU,EAAEC,WAAW,EAAE;IACnC,KAAK,CAACD,UAAU,EAAEC,WAAW,CAAC;IAC9B,IAAI,CAACC,YAAY,GAAG,IAAAC,uBAAc,EAAC,IAAI,CAACC,aAAa,CAAC,CAAC,CAAC;IACxD,IAAI,CAACC,gBAAgB,CAAC,CAAC;EACzB;;EAEA;AACF;AACA;AACA;AACA;AACA;EACEA,gBAAgBA,CAAA,EAAG;IACjB,MAAMC,gBAAgB,GAAG,IAAI,CAACH,cAAc,CAAC,CAAC,CAACI,MAAM,CAACC,UAAU,IAAI;MAClE,OACE,CAAC,IAAI,CAACC,aAAa,CAACD,UAAU,CAAC,IAC/B,CAAC,IAAAE,gBAAQ,EAACC,oCAA2B,EAAEH,UAAU,CAAC,IAClD,CAAC,IAAI,CAACI,qBAAqB,CAACJ,UAAU,CAAC,IACvC,CAAC,IAAAE,gBAAQ,EAACG,uCAAyB,EAAEL,UAAU,CAAC;IAEpD,CAAC,CAAC;IAEF,IAAI,CAACM,UAAU,CAACR,gBAAgB,CAACS,MAAM,GAAG,CAAC,CAAC;EAC9C;;EAEA;AACF;AACA;AACA;AACA;AACA;AACA;AACA;EACEN,aAAaA,CAACD,UAAU,EAAE;IACxB,OAAOA,UAAU,CAACQ,KAAK,CAACnB,eAAe,CAAC,KAAK,IAAI;EACnD;;EAEA;AACF;AACA;AACA;AACA;AACA;AACA;AACA;EACEe,qBAAqBA,CAACJ,UAAU,EAAE;IAChC,MAAMS,iBAAiB,GAAGvB,gBAAgB,CAACc,UAAU,EAAE,IAAI,CAACJ,aAAa,CAAC,CAAC,CAAC;IAC5E,IAAIc,gBAAgB,GAAGvB,oBAAoB,CAAC,CAAC,OAAO,EAAE,MAAM,CAAC,EAAE,IAAI,CAACS,aAAa,CAAC,CAAC,CAAC;;IAEpF;IACA,IAAIa,iBAAiB,CAACF,MAAM,KAAK,CAAC,IAAIG,gBAAgB,CAACH,MAAM,KAAK,CAAC,EAAE;MACnE,OAAO,KAAK;IACd;IAEAG,gBAAgB,GAAG,IAAAC,WAAG,EAACD,gBAAgB,EAAE,OAAO,CAAC;IACjD,MAAME,iBAAiB,GAAGH,iBAAiB,CAAC,CAAC,CAAC;IAC9C,OAAO,IAAAP,gBAAQ,EAACQ,gBAAgB,EAAEE,iBAAiB,CAACC,KAAK,GAAGD,iBAAiB,CAACJ,KAAK,CAACD,MAAM,GAAG,CAAC,CAAC;EACjG;AACF;AAAC,IAAAO,QAAA,GAAAC,OAAA,CAAAjC,OAAA,GAEcQ,YAAY","ignoreList":[]}

package/build/languageProcessing/languages/el/Researcher.js

@@ -0,0 +1,55 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _index = require("../../../index");
+var _firstWordExceptions = _interopRequireDefault(require("./config/firstWordExceptions"));
+var _transitionWords = _interopRequireDefault(require("./config/transitionWords"));
+var _twoPartTransitionWords = _interopRequireDefault(require("./config/twoPartTransitionWords"));
+var _functionWords = _interopRequireDefault(require("./config/functionWords"));
+var _getStemmer = _interopRequireDefault(require("./helpers/getStemmer"));
+var _getClauses = _interopRequireDefault(require("./helpers/getClauses"));
+var _isPassiveSentence = _interopRequireDefault(require("./helpers/isPassiveSentence"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+const {
+  AbstractResearcher
+} = _index.languageProcessing;
+
+// All config
+
+// All helpers
+
+/**
+ * The researcher contains all the researches, helpers, data, and config.
+ */
+class Researcher extends AbstractResearcher {
+  /**
+   * Constructor
+   * @param {Paper} paper The Paper object that is needed within the researches.
+   * @constructor
+   */
+  constructor(paper) {
+    super(paper);
+
+    // Deletes researches that are not available for languages that we haven't supported yet.
+    delete this.defaultResearches.getFleschReadingScore;
+    Object.assign(this.config, {
+      language: 'el',
+      functionWords: _functionWords.default,
+      passiveConstructionType: 'morphologicalAndPeriphrastic',
+      transitionWords: _transitionWords.default,
+      twoPartTransitionWords: _twoPartTransitionWords.default,
+      firstWordExceptions: _firstWordExceptions.default.firstWords,
+      secondWordExceptions: _firstWordExceptions.default.secondWords
+    });
+    Object.assign(this.helpers, {
+      getStemmer: _getStemmer.default,
+      getClauses: _getClauses.default,
+      isPassiveSentence: _isPassiveSentence.default
+    });
+  }
+}
+exports.default = Researcher;
+//# sourceMappingURL=Researcher.js.map

package/build/languageProcessing/languages/el/Researcher.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"Researcher.js","names":["_index","require","_firstWordExceptions","_interopRequireDefault","_transitionWords","_twoPartTransitionWords","_functionWords","_getStemmer","_getClauses","_isPassiveSentence","e","__esModule","default","AbstractResearcher","languageProcessing","Researcher","constructor","paper","defaultResearches","getFleschReadingScore","Object","assign","config","language","functionWords","passiveConstructionType","transitionWords","twoPartTransitionWords","firstWordExceptions","firstWords","secondWordExceptions","secondWords","helpers","getStemmer","getClauses","isPassiveSentence","exports"],"sources":["../../../../src/languageProcessing/languages/el/Researcher.js"],"sourcesContent":["import {languageProcessing} from '../../../index';\nconst {AbstractResearcher} = languageProcessing;\n\n// All config\nimport firstWordExceptions from './config/firstWordExceptions';\nimport transitionWords from './config/transitionWords';\nimport twoPartTransitionWords from './config/twoPartTransitionWords';\nimport functionWords from './config/functionWords';\n\n// All helpers\nimport getStemmer from './helpers/getStemmer';\nimport getClauses from './helpers/getClauses';\nimport isPassiveSentence from './helpers/isPassiveSentence';\n\n/**\n * The researcher contains all the researches, helpers, data, and config.\n */\nexport default class Researcher extends AbstractResearcher {\n  /**\n   * Constructor\n   * @param {Paper} paper The Paper object that is needed within the researches.\n   * @constructor\n   */\n  constructor(paper) {\n    super(paper);\n\n    // Deletes researches that are not available for languages that we haven't supported yet.\n    delete this.defaultResearches.getFleschReadingScore;\n\n    Object.assign(this.config, {\n      language: 'el',\n      functionWords,\n      passiveConstructionType: 'morphologicalAndPeriphrastic',\n      transitionWords,\n      twoPartTransitionWords,\n      firstWordExceptions: firstWordExceptions.firstWords,\n      secondWordExceptions: firstWordExceptions.secondWords\n    });\n\n    Object.assign(this.helpers, {\n      getStemmer,\n      getClauses,\n      isPassiveSentence\n    });\n  }\n}\n"],"mappings":";;;;;;AAAA,IAAAA,MAAA,GAAAC,OAAA;AAIA,IAAAC,oBAAA,GAAAC,sBAAA,CAAAF,OAAA;AACA,IAAAG,gBAAA,GAAAD,sBAAA,CAAAF,OAAA;AACA,IAAAI,uBAAA,GAAAF,sBAAA,CAAAF,OAAA;AACA,IAAAK,cAAA,GAAAH,sBAAA,CAAAF,OAAA;AAGA,IAAAM,WAAA,GAAAJ,sBAAA,CAAAF,OAAA;AACA,IAAAO,WAAA,GAAAL,sBAAA,CAAAF,OAAA;AACA,IAAAQ,kBAAA,GAAAN,sBAAA,CAAAF,OAAA;AAA4D,SAAAE,uBAAAO,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAX5D,MAAM;EAACG;AAAkB,CAAC,GAAGC,yBAAkB;;AAE/C;;AAMA;;AAKA;AACA;AACA;AACe,MAAMC,UAAU,SAASF,kBAAkB,CAAC;EACzD;AACF;AACA;AACA;AACA;EACEG,WAAWA,CAACC,KAAK,EAAE;IACjB,KAAK,CAACA,KAAK,CAAC;;IAEZ;IACA,OAAO,IAAI,CAACC,iBAAiB,CAACC,qBAAqB;IAEnDC,MAAM,CAACC,MAAM,CAAC,IAAI,CAACC,MAAM,EAAE;MACzBC,QAAQ,EAAE,IAAI;MACdC,aAAa,EAAbA,sBAAa;MACbC,uBAAuB,EAAE,8BAA8B;MACvDC,eAAe,EAAfA,wBAAe;MACfC,sBAAsB,EAAtBA,+BAAsB;MACtBC,mBAAmB,EAAEA,4BAAmB,CAACC,UAAU;MACnDC,oBAAoB,EAAEF,4BAAmB,CAACG;IAC5C,CAAC,CAAC;IAEFX,MAAM,CAACC,MAAM,CAAC,IAAI,CAACW,OAAO,EAAE;MAC1BC,UAAU,EAAVA,mBAAU;MACVC,UAAU,EAAVA,mBAAU;MACVC,iBAAiB,EAAjBA;IACF,CAAC,CAAC;EACJ;AACF;AAACC,OAAA,CAAAxB,OAAA,GAAAG,UAAA","ignoreList":[]}

package/build/languageProcessing/languages/el/config/firstWordExceptions.js

@@ -0,0 +1,33 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+/**
+ * Returns an array with exceptions for the sentence beginning research.
+ * @type {Array} The array filled with exceptions.
+ */
+const firstWords = [
+// Definite articles:
+"o", "του", "τον ", "ο", "των", "τους", "η", "της", "την", "τις", "το", "τα",
+// Indefinite articles:
+"ένας", "ενός", "έναν", "μία", "μίας", "μία", "ένα", "μια", "μιας", "μια",
+// Numbers 1-10:
+"ένα", "δύο", "τρία", "τέσσερα", "πέντε ", "έξι", "επτά", "εφτά", "οκτώ", "οχτώ", "εννέα", "εννιά", "δέκα",
+// Demonstratives:
+"αυτός", "αυτού", "αυτόν", "αυτοί", "αυτών", "αυτούς", "αυτή", "αυτής", "αυτή", "αυτό", "αυτά", "εκείνος", "εκείνου", "εκείνον", "εκείνοι", "εκείνων", "εκείνη", "εκείνης", "εκείνη", "εκείνες", "εκείνο", "εκείνα", "τέτοιος", "τέτοιου", "τέτοιον", "τέτοιοι", "τέτοιων", "τέτοιους", "τέτοια", "τέτοιας", "τέτοιαν", "τέτοιες", "τέτοιο", "τέτοια", "τόσος", "τόσου", "τόσον", "τόσοι", "τόσων", "τόσους", "τόση", "τόσης", "τόσες", "τόσο", "τόσα", "τούτος", "τούτου", "τούτον", "τούτοι", "τούτων", "τούτους", "τούτη ", "τούτης", "τούτην ", "τούτες", "τούτο", "τούτα", "εδώ", "εκεί"];
+
+/**
+ * Returns an array of words that can occur after demonstrative pronouns.
+ *
+ * @type {string[]} The array filled with exceptions.
+ */
+const secondWords = [
+// Definite articles and relative pronouns
+"o", "του", "τον ", "ο", "των", "τους", "η", "της", "την", "τις", "το", "τα", "που", "τον", "οι"];
+var _default = exports.default = {
+  firstWords: firstWords,
+  secondWords: secondWords
+};
+//# sourceMappingURL=firstWordExceptions.js.map

package/build/languageProcessing/languages/el/config/firstWordExceptions.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"firstWordExceptions.js","names":["firstWords","secondWords","_default","exports","default"],"sources":["../../../../../src/languageProcessing/languages/el/config/firstWordExceptions.js"],"sourcesContent":["/**\n * Returns an array with exceptions for the sentence beginning research.\n * @type {Array} The array filled with exceptions.\n */\nconst firstWords = [\n\t// Definite articles:\n\t\"o\", \"του\", \"τον \", \"ο\", \"των\", \"τους\", \"η\", \"της\", \"την\", \"τις\", \"το\", \"τα\",\n\t// Indefinite articles:\n\t\"ένας\", \"ενός\", \"έναν\", \"μία\", \"μίας\", \"μία\", \"ένα\", \"μια\", \"μιας\", \"μια\",\n\t// Numbers 1-10:\n\t\"ένα\", \"δύο\", \"τρία\", \"τέσσερα\", \"πέντε \", \"έξι\", \"επτά\", \"εφτά\", \"οκτώ\", \"οχτώ\", \"εννέα\", \"εννιά\", \"δέκα\",\n\t// Demonstratives:\n\t\"αυτός\", \"αυτού\", \"αυτόν\", \"αυτοί\", \"αυτών\", \"αυτούς\", \"αυτή\", \"αυτής\", \"αυτή\", \"αυτό\", \"αυτά\", \"εκείνος\", \"εκείνου\",\n\t\"εκείνον\", \"εκείνοι\", \"εκείνων\", \"εκείνη\", \"εκείνης\", \"εκείνη\", \"εκείνες\", \"εκείνο\", \"εκείνα\", \"τέτοιος\", \"τέτοιου\",\n\t\"τέτοιον\", \"τέτοιοι\", \"τέτοιων\", \"τέτοιους\", \"τέτοια\", \"τέτοιας\", \"τέτοιαν\", \"τέτοιες\", \"τέτοιο\", \"τέτοια\", \"τόσος\",\n\t\"τόσου\", \"τόσον\", \"τόσοι\", \"τόσων\", \"τόσους\", \"τόση\", \"τόσης\", \"τόσες\", \"τόσο\", \"τόσα\", \"τούτος\", \"τούτου\", \"τούτον\",\n\t\"τούτοι\", \"τούτων\", \"τούτους\", \"τούτη \", \"τούτης\", \"τούτην \", \"τούτες\", \"τούτο\", \"τούτα\", \"εδώ\", \"εκεί\",\n];\n\n/**\n * Returns an array of words that can occur after demonstrative pronouns.\n *\n * @type {string[]} The array filled with exceptions.\n */\nconst secondWords = [\n\t// Definite articles and relative pronouns\n\t\"o\",\n\t\"του\",\n\t\"τον \",\n\t\"ο\",\n\t\"των\",\n\t\"τους\",\n\t\"η\",\n\t\"της\",\n\t\"την\",\n\t\"τις\",\n\t\"το\",\n\t\"τα\",\n\t\"που\",\n\t\"τον\",\n\t\"οι\",\n];\n\nexport default {\n\tfirstWords: firstWords,\n\tsecondWords: secondWords,\n};\n"],"mappings":";;;;;;AAAA;AACA;AACA;AACA;AACA,MAAMA,UAAU,GAAG;AAClB;AACA,GAAG,EAAE,KAAK,EAAE,MAAM,EAAE,GAAG,EAAE,KAAK,EAAE,MAAM,EAAE,GAAG,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,IAAI,EAAE,IAAI;AAC5E;AACA,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,MAAM,EAAE,KAAK;AACzE;AACA,KAAK,EAAE,KAAK,EAAE,MAAM,EAAE,SAAS,EAAE,QAAQ,EAAE,KAAK,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM;AAC1G;AACA,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,QAAQ,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,SAAS,EAAE,SAAS,EACpH,SAAS,EAAE,SAAS,EAAE,SAAS,EAAE,QAAQ,EAAE,SAAS,EAAE,QAAQ,EAAE,SAAS,EAAE,QAAQ,EAAE,QAAQ,EAAE,SAAS,EAAE,SAAS,EACnH,SAAS,EAAE,SAAS,EAAE,SAAS,EAAE,UAAU,EAAE,QAAQ,EAAE,SAAS,EAAE,SAAS,EAAE,SAAS,EAAE,QAAQ,EAAE,QAAQ,EAAE,OAAO,EACnH,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,QAAQ,EAAE,MAAM,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,QAAQ,EAAE,QAAQ,EAAE,QAAQ,EACpH,QAAQ,EAAE,QAAQ,EAAE,SAAS,EAAE,QAAQ,EAAE,QAAQ,EAAE,SAAS,EAAE,QAAQ,EAAE,OAAO,EAAE,OAAO,EAAE,KAAK,EAAE,MAAM,CACvG;;AAED;AACA;AACA;AACA;AACA;AACA,MAAMC,WAAW,GAAG;AACnB;AACA,GAAG,EACH,KAAK,EACL,MAAM,EACN,GAAG,EACH,KAAK,EACL,MAAM,EACN,GAAG,EACH,KAAK,EACL,KAAK,EACL,KAAK,EACL,IAAI,EACJ,IAAI,EACJ,KAAK,EACL,KAAK,EACL,IAAI,CACJ;AAAC,IAAAC,QAAA,GAAAC,OAAA,CAAAC,OAAA,GAEa;EACdJ,UAAU,EAAEA,UAAU;EACtBC,WAAW,EAAEA;AACd,CAAC","ignoreList":[]}

package/build/languageProcessing/languages/el/config/functionWords.js

@@ -0,0 +1,47 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = exports.all = void 0;
+var _transitionWords = require("./transitionWords");
+var _transformWordsWithHyphens = _interopRequireDefault(require("../../../helpers/transform/transformWordsWithHyphens"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Returns an array of Greek function words.
+ *
+ * @returns {Array} The array filled with the function words.
+ */
+const articles = ["μιανής", "στους", "στον", "στου", "στην", "στης", "ένας", "ενός", "έναν", "μίας", "μιάς", "την", "του", "τον", "των", "τις", "της", "στο", "στα", "μία", "μια", "ένα", "το", "η ", "τα", "οι", "τη", "ο"];
+const cardinalNumbers = ["ένα", "δύο ", "τρία ", "τέσσερα", "πέντε", "έξι", "εφτά", "οχτώ", "εννιά", "οκτώ", "εννέα", "δέκα", "εκατό", "χίλια", "εκατομμύριο", "εκατομμύρια", "δισεκατομμύριο", "δισεκατομμύρια", "έντεκα", "ένδεκα", "δώδεκα", "δεκατρία", "δεκατέσσερα", "δεκαπέντε", "δεκαέξι", "δεκαεπτά", "δεκαοκτώ", "δεκαεννέα", "είκοσι"];
+const otherNumbers = ["πρώτος", "δεύτερος", "τρίτος", "τέταρτος", "πέμπτος", "έκτος", "έβδομος", "όγδοος", "ένατος", "δέκατος", "πρώτη", "δεύτερη", "τρίτη", "τέταρτη", "πέμπτη", "έκτη", "έβδομη", "όγδοη", "ένατη", "δέκατη", "πρώτο ", "δεύτερο", "τρίτο", "τέταρτο", "πέμπτο", "έκτο", "έβδομο", "όγδοο", "ένατο", "δέκατο", "διπλάσιος", "διπλάσια", "διπλάσιο", "τριπλάσιος", "τριπλάσια", "τριπλάσιο", "διπλός", "διπλή", "τριπλός", "τριπλή", "χίλιοι", "χίλιες", "εκατοντάδες", "χιλιάδες"];
+const fractions = ["μισός", "μισή", "μισό", "τέταρτο", "τρίτο", "ολόκληρο", "ολόκληρος"];
+
+// Including the personal pronouns with cases.
+const personalPronouns = ["εγώ", "εσύ", "αυτός", "αυτή", "αυτό", "εμείς", "εσείς", "αυτοί", "αυτές", "αυτά", "αυτούς", "εμένα", "εσένα", "αυτών", "μένα", "σένα", "εμάς", "εσάς", "μου", "σου", "μας", "σας", "με", "σε"];
+const demonstrativePronouns = ["τέτοιους", "εκείνος", "εκείνου", "εκείνον", "εκείνοι", "εκείνων", "εκείνης", "εκείνες", "τέτοιος", "τέτοιου", "τέτοιον", "τέτοιοι", "τέτοιων", "τέτοιας", "τέτοιαν", "τέτοιες", "τούτους", "τούτην ", "εκείνη", "εκείνη", "εκείνο", "εκείνα", "τέτοια", "τέτοιο", "τέτοια", "τόσους", "τούτος", "τούτου", "τούτον", "τούτοι", "τούτων", "τούτη ", "τούτης", "τούτες", "αυτού", "αυτόν", "αυτής", "τόσος", "τόσου", "τόσον", "τόσοι", "τόσων", "τόσης", "τόσες", "τούτο", "τούτα", "τόση", "τόσο", "τόσα", "εκεί", "εδώ"];
+
+// Including singular and plural interrogatives.
+const interrogatives = ["ποιανού", "ποιανής", "ποιανών", "ποιους", "πόσους", "ποιος", "ποιου", "ποιον", "ποιας", "πόσος", "πόσου", "πόσον", "πόσης", "ποιοι", "ποιων", "ποιες", "πόσοι", "πόσων", "πόσες", "ποια", "ποιο", "πόση", "πόσα", "τί", "τι"];
+const interrogativeAdverbs = ["πώς", "πού", "πόσο", "πότε"];
+
+// Including quantifiers for adjectives and adverbs.
+const quantifiers = ["περισσότερο", "λιγότερο", "ελάχιστα", "καθόλου", "αρκετά", "εξίσου", "κάπως", "τόσο ", "πολύ", "τόσο", "πιο", "όσο"];
+const reflexivePronouns = ["εαυτός", "εαυτού", "εαυτό", "εαυτούς"];
+const possessivePronouns = ["δικός", "δικού", "δικό", "δική", "δικής", "τους", "δικοί", "δικών", "δικούς", "δικές", "δικά"];
+const indefinitePronouns = ["κάμποσου", "κάμποσον", "κάμποση", "κάμποσης ", "κάμποσο", "τίποτε", "καθένας", "καθενός", "καθένα ", "καθεμία", "καθεμιά", "καθεμίας", "καθεμιάς", "καθέναν", "δείνα", "τάδε", "μερικοί", "μερικών", "μερικούς", "μερικές", "μερικά", "κάποιοι", "κάποιων", "κάποιους", "κάποιες", "κάποια", "άλλοι", "άλλων", "αλλονών", "άλλους", "άλλες", "άλλα", "κάμποσοι", "κάμποσων", "κάμποσες", "κάμποσα"];
+const prepositions = ["σε", "με", "από", "για", "ως", "πριν", "προς", "σαν", "αντί", "δίχως", "έως", "κατά", "μετά", "μέχρι", "χωρίς", "παρά", "εναντίον", "εξαιτίας", "μεταξύ", "ίσαμε", "άνευ", "αμφί", "ανά", "διά", "εκ", "εις", "εξ", "εκτός", "εν", "ένεκα", "εντός", "επί", "λόγω", "περί", "πρό", "συν", "υπέρ", "υπό", "χάριν", "χάρη"];
+const particles = ["δεν", "θα", "δεν", "μη", "μην", "όχι", "ναι", "ας", "για", "μα"];
+const conjuntions = ["να", "και", "που", "ότι", "αν", "αλλά", "ούτε", "ουδέ", "μηδέ", "μήτε", "ή", "είτε", "μα", "παρά", "όμως", "ωστόσο", "ενώ", "μολονότι", "μόνο", "μόνο που", "λοιπόν", "ώστε", "άρα", "επομένως", "οπότε", "δηλαδή", "πως", "μην", "μήπως", "άμα", "όταν", "καθώς", "αφού", "αφότου", "πριν", "μόλις", "προτού", "ώσπου", "ωσότου", "σαν", "γιατί", "επειδή"];
+const interviewVerbs = ["συνηθίζεται", "μπορούσαμε", "ενδέχεται", "εξαρτάται", "εννοείται", "παίρνουμε", "είθισται", "μπορούμε", "μπορείτε", "υπάρχουν", "παίρνεις", "παίρνετε", "παίρνουν", "βασικούς", "μπορούμε", "είμαστε", "είσαστε", "υπάρχει", "μπορείς", "μπορούν", "κάνουμε", "υπήρχαν", "γίνεται", "γινόταν", "παίρνει", "βάζουμε", "δίνουμε", "μπορεί", "παίρνω", "πρέπει", "έχουμε", "πήγαμε", "πήγατε", "κάνεις", "κάνετε", "κάνουν", "έκανες", "κάναμε", "κάνατε", "έκαναν", "υπήρχε", "πήραμε", "πήρατε", "πήρανε", "ρίχνει", "φάγαμε", "βάζεις", "βάζετε", "βάζουν", "έβαλες", "βάλαμε", "βάλατε", "έβαλαν", "βάλανε", "δίνεις", "δίνεις", "δίνετε", "δίνουν", "έδωσες", "έδωσες", "δώσαμε", "δώσατε", "έδωσαν", "δώσανε", "έδινες", "δίναμε", "δίνατε", "δίνανε", "έδιναν", "είχαμε", "είχατε", "είναι", "είμαι", "είσαι", "είστε", "ρίχνω", "μπορώ", "πήγες", "πήγαν", "κάνει", "έκανα", "έκανε", "πήρες", "πήραν", "έριξα", "έριξε", "τρώει", "τρώμε", "έφαγε", "βάζει", "έβαλα", "έβαλε", "έδωσα", "έδινα", "έδινε", "έχεις", "έχετε", "έχουν", "είχες", "είχαν", "κάνω", "τρώω", "βάζω", "δίνω", "πάμε", "πάει", "πάμε", "πάτε", "πάνε", "πήγα", "πήγε", "πήρε", "έχει", "είχα", "είχε", "πάω", "έχω", "πας"];
+const intensifiers = ["πολύ", "παρά ", "παρα", "απίστευτα", "εκπληκτικά", "αναπάντεχα", "αφάνταστα", "πραγματικά", "εντελώς", "απόλυτα", "καθολικά", "τελείως"];
+const auxiliariesAndDelexicalizedVerbs = ["συνηθίζεται", "ενδέχεται", "εξαρτάται", "εννοείται", "είθισται", "είμαστε", "είσαστε", "υπάρχει", "μπορεί", "παίρνω", "πρέπει", "έχουμε", "είναι", "είμαι", "είσαι", "είστε", "ρίχνω", "μπορώ", "κάνω", "τρώω", "βάζω", "δίνω", "πάμε", "πάω", "έχω"];
+const generalAdjectivesAdverbs = ["καλός", "καλά", "καλή", "καλύτερος", "καλύτερη", "σοβαρά", "ωραίος", "ωραία", "ωραίο", "απλός", "απλή", "απλό", "περίπλοκος", "περίπλοκη", "περίπλοκο", "μεγάλο", "μεγαλύτερος", "βασική", "βασικός", "βασικό", "ουσιαστικός", "κανονικός", "κανονική", "κανονικό", "άσχημο", "τρομερό", "απαίσιο", "αδιανόητο", "μέσος", "πραγματικός", "πραγματική", "πραγματικό", "πρώην", "σπάνιος", "σπάνια", "συνηθισμένος ", "συνηθισμένη", "συνηθισμένο", "σχετικός", "σχετική", "σχετικό", "καλύτερα", "τέλεια", "υπέροχα", "έντονα", "παραλίγο", "απλά", "κυρίως", "συνήθως", "ευθέως", "συνεχώς", "αδιάκοπα", "ασταμάτητα", "ατελείωτα", "ατέρμονα", "βασικά", "ουσιαστικά", "κανονικά", "άσχημα", "εντάξει", "τελικά", "φυσικά", "μπροστά", "πίσω", "επάνω", "κάτω", "ευτυχώς", "δυστυχώς", "ξαφνικά", "ειλικρινά", "απροσδόκητα", "απότομα", "ανάμεσα", "κοντά", "σιμά", "μακριά", "δίπλα", "σχετικά"];
+const interjections = ["α", "αα", "αχ", "αι", "αλί", "αλίμονο", "αμάν", "αμέ", "αμποτε", "άιντε", "άντε", "άου", "άχου", "αχού", "βαχ", "βουρ ", "βρε", "ε", "ει", "εμ", "επ", "ζήτω", "εύγε", "μμμ", "μπα", "μπαμ", "μπράβο", "μωρέ", "μωρή", "ω", "ου", "ούου", "ουστ", "οιμέ", "οϊμέ", "ωπ", "οπ", "πωπω", "ποπο", "απαπα", "ουφ", "ώπα", "ώπατης", "όπα", "όπατης", "ωχ", "οχ", "όχου", "ώχου", "όφου", "ποπό", "πωπώ", "πουφ", "πριτς", "πφ", "ρε", "σουτ", "τσου", "τσα", "φτου", "χα", "χαχαχα", "χμ", "ωω", "ωωω", "ωχού", "ουάου"];
+const recipeWords = ["γραμ.", "γραμμ.", "γραμμάρια", "κ/γ", "κ.γ.", "κ.σ.", "γρ.", "ματσ.", "κιλό", "φλ.", "φλυτζάνι", "κούπα", "ποτ.", "ποτήρι", "σκ.", "ξύσμα", "φλούδα", "λίτρο", "λίτρα"];
+const timeWords = ["δευτερόλεπτο", "δευτερόλεπτα", "δεύτερα", "ώρα", "ώρας", "τέταρτο", "μισάωρο", "ώρες", "μέρα", "μέρας", "μέρες", "ημέρα", "ημέρες", "σήμερα", "αύριο", "εχθές", "χθές", "βδομάδα", "βδομάδες", "βδομάδας", "εβδομάδα", "εβδομάδες", "μισαωράκι", "τεταρτάκι", "δεκάλεπτο", "πεντάλεπτο", "φέτος", "πέρσι", "χρόνος", "πέρυσι", "χρόνου", "πρόπερσι", "προχθές"];
+const vagueNouns = ["πράγμα", "πράγματα", "υπόθεση", "περίπτωση", "πρόβλημα", "προβλήματα", "αντικείμενο", "αντικείμενα", "θέμα", "θέματα", "περίσταση", "συνθήκες", "περιστάσεις", "ζήτημα", "ζητήματα", "ζητημάτων", "υποθέσεις", "γεγονός", "γεγονότα", "κατάσταση", "καταστάσεις", "ουσία", "τρόπος", "μέθοδος", "παράγοντας", "παράγοντες", "αιτία", "επίπτωση", "αιτίες", "επιπτώσεις", "μέρος", "μέρη", "άποψη", "απόψεις", "γνώμη", "γνώμες", "άτομο", "άτομα", "ομάδα", "πραγματικότητα", "διαφορά", "διαφορές", "ομοιότητες"];
+const titles = ["δεσποινίς", "καθηγητής", "διδάκτωρ", "κύριος", "κύριοι", "κυρίες", "καθηγ", "κυρία", "διδα", "καθ", "κος", "δρ", "κα"];
+const all = exports.all = (0, _transformWordsWithHyphens.default)([].concat(articles, cardinalNumbers, otherNumbers, fractions, personalPronouns, demonstrativePronouns, interrogatives, interrogativeAdverbs, quantifiers, reflexivePronouns, possessivePronouns, indefinitePronouns, prepositions, particles, conjuntions, interviewVerbs, intensifiers, auxiliariesAndDelexicalizedVerbs, generalAdjectivesAdverbs, interjections, recipeWords, timeWords, vagueNouns, titles, _transitionWords.singleWords));
+var _default = exports.default = all;
+//# sourceMappingURL=functionWords.js.map