#include "common.h"

#include <unordered_map>

#include <string>

//

// All pos data comes from original spanish dictionary. If not there, we dont know about it

//

// NOTE: the ComputeSpanish1... code tests using correctly accented forms of Spanish words.

// It is assumed that if the user accents a character, it is correct. If this becomes a problem, we will use

// spellcheck to permute that as well as incorrectly unaccented characters.

// computespanish uses all of the original dictionary (not seeing UNIVERSAL merged words) and it not

// allowed to change properties or systemflags of words, except at at the computespanish outer layer.

// For this (and other treetagger-based dictionaries), the only reliable data is that lemmas are there, marked

// by their part of speech. While it contains common conjugations, we cannot assume all are there. Nor

// is there data on additional attributes like gender and plurality (in fact often it marks a singular noun as both

// singular and plural). So the task of ComputeSpanish1 is two-fold. First, to determine for spellcheck

// if a word in user input that is NOT recognized, can be determined to be a conjugation of a known lemma.

// Second, for GetPosData, to return the set of all possible parts of speech and ancillary data like lemma, gender,

// plurality, and embedded object referencing for PosTagging.

// Currently this is not in the dictionary as static data because we would have to compute it using this function anyway

// to write the revised dictionary. And if this code is wrong and we already used it to rewrite the dictionary flags

// of the source, then recovering from faulty markings may be difficult.

// primary entry point for conjugation processing

uint64 ComputeSpanish(int at, const char* original, WORDP& entry, WORDP& canonical, uint64& sysflags);

uint64 ComputeSpanish1(int at, const char* original, WORDP& entry, WORDP& canonical, uint64& sysflags);

typedef struct IrregularSpanishInfo

{

const char* lemma;

const char* original; // conjugated form

const char* stem; // suffixes go against this

const uint64 properties;

const uint64 sysFlags;

string unaccented;

} IrregularSpanishInfo;

static IrregularSpanishInfo irregularSpanishVerbs[] =

{// any stem that is a blank means we dont know, and it may not matter

// we deliver SIMPLE PAST (PRETERITE) and IMPERFECT past

// we deliver spanish FUTURE and conditional tenses as FUTURE

// preterite past

{"ser","fue","fu",VERB | VERB_PAST,0, ""}, // él fue, ellos fueron

{"ser","fueron","fu", VERB | VERB_PAST,0, ""},

{"estar","estuve","estuv", VERB | VERB_PAST,PRONOUN_SINGULAR | PRONOUN_I, ""}, //yo estuve, tu estuviste, él estuvo, nosotros estuvimos, vosotros estuvisteis, ellos estuvieron

{"estar","estuviste","estuv", VERB | VERB_PAST,PRONOUN_SINGULAR | PRONOUN_YOU, ""}, //yo estuve, tu estuviste, él estuvo, nosotros estuvimos, vosotros estuvisteis, ellos estuvieron

{"estar","estuviseis","estuv", VERB | VERB_PAST,PRONOUN_PLURAL | PRONOUN_YOU, ""}, //yo estuve, tu estuviste, él estuvo, nosotros estuvimos, vosotros estuvisteis, ellos estuvieron

{"tener","tuve","ten", VERB | VERB_PAST,PRONOUN_SINGULAR | PRONOUN_I, ""}, // - yo tuve, él tuvo

{"tener","tuviste","ten", VERB | VERB_PAST,PRONOUN_SINGULAR | PRONOUN_YOU, ""}, // - yo tuve, él tuvo

{"tener","tuvo","ten", VERB | VERB_PAST,PRONOUN_SINGULAR | PRONOUN_HE_SHE_IT, ""}, // - yo tuve, él tuvo

{"tener","tuvimos","ten", VERB | VERB_PAST,PRONOUN_PLURAL | PRONOUN_I, ""}, // - yo tuve, él tuvo

{"tener","tuvisteis","ten", VERB | VERB_PAST,PRONOUN_PLURAL | PRONOUN_YOU, ""}, // - yo tuve, él tuvo

{"tener","tuvieron","ten", VERB | VERB_PAST,PRONOUN_PLURAL | PRONOUN_HE_SHE_IT, ""}, // - yo tuve, él tuvo

{"poder","pude","pud", VERB | VERB_PAST,PRONOUN_SINGULAR | PRONOUN_I, ""},

{"poder","pudiste","pud", VERB | VERB_PAST,PRONOUN_SINGULAR | PRONOUN_YOU, ""},

{"poder","pudo","pud", VERB | VERB_PAST,PRONOUN_SINGULAR | PRONOUN_HE_SHE_IT, ""},

{"poder","pudimos","pud", VERB | VERB_PAST,PRONOUN_PLURAL | PRONOUN_I, ""},

{"poder","pudisteis","pud", VERB | VERB_PAST,PRONOUN_PLURAL | PRONOUN_YOU, ""},

{"poder","pudieron","pud", VERB | VERB_PAST,PRONOUN_PLURAL | PRONOUN_YOU | PRONOUN_HE_SHE_IT, ""},

{"hacer","hice","hic", VERB | VERB_PAST,PRONOUN_SINGULAR | PRONOUN_I, ""}, // most subjects yo hice,

{"hacer","hiciste","hic", VERB | VERB_PAST,PRONOUN_SINGULAR | PRONOUN_YOU, ""}, // most subjects yo hice,

{"hacer","hicimos","hic", VERB | VERB_PAST,PRONOUN_PLURAL | PRONOUN_I, ""}, // most subjects yo hice,

{"hacer","hicisteis","hic", VERB | VERB_PAST,PRONOUN_PLURAL | PRONOUN_YOU, ""}, // most subjects yo hice,

{"hacer","hicieron","hic", VERB | VERB_PAST,PRONOUN_PLURAL, ""}, // most subjects yo hice,

{"poner","puse","pus", VERB | VERB_PAST,0, ""}, // yo puse, él puso

{"poner","puso","pus", VERB | VERB_PAST,0, ""}, // yo puse, él puso

{"decir","dije","dij", VERB | VERB_PAST,0, ""}, // yo dije, él dijo

{"decir","dijiste","dij", VERB | VERB_PAST,0, ""},

{"decir","dijo"," dij", VERB | VERB_PAST,0, ""},

{"decir","dijimos"," dij", VERB | VERB_PAST,PRONOUN_PLURAL | PRONOUN_I, ""},

{"decir","dijisties"," dij", VERB | VERB_PAST,PRONOUN_PLURAL | PRONOUN_YOU, ""},

{"decir","dijeron"," dij", VERB | VERB_PAST,PRONOUN_PLURAL, ""},

{"ver","vi","vi", VERB | VERB_PAST,0, ""},

{"ver","vio","vi", VERB | VERB_PAST,0, ""},

{"querer","quise","quis", VERB | VERB_PAST,0, ""}, // yo quise, él quiso

{"querer","quiso","quis", VERB | VERB_PAST,0, ""},

// in present tense, various irregular verbs vary in their 1stperson singular form and conjugate normally otherwise

{"caber","quepo","cab", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"caer","caigo","ca", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"coger","cojo","cog", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"comer","come","com", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU | PRONOUN_HE_SHE_IT | VERB_IMPERATIVE, ""},

{"conocer","conozco","conoc", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"contar","cuento","cont", VERB | VERB_PRESENT, PRONOUN_I | PRONOUN_SINGULAR, ""},

{"dar","doy"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"decir","digo","dec", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"decir","dices","dec", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU, ""},

{"decir","dice","dec", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU, ""},

{"decir","dicen","dec", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_PLURAL, ""},

{"estar","estoy","estuv", VERB | VERB_PRESENT,PRONOUN_SINGULAR | PRONOUN_I, ""},

{"estar",u8"está","estuv", VERB | VERB_PRESENT,PRONOUN_SINGULAR | PRONOUN_HE_SHE_IT, ""},

{"estar",u8"están","estuv", VERB | VERB_PRESENT,PRONOUN_PLURAL | PRONOUN_HE_SHE_IT, ""},

{"hacer","hago"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"mostrar","muestro","muestr", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"poner","pongo"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"salir","salgo"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"sentir","siento","sent", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"sentir","sientes","sent", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU, ""},

{"sentir","siente","sent", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_HE_SHE_IT | PRONOUN_YOU | VERB_IMPERATIVE | PRONOUN_INDIRECTOBJECT_SINGULAR | PRONOUN_INDIRECTOBJECT_YOU, ""},

{"sentir","sienta","sent", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{"sentir","sientas","sent", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_HE_SHE_IT | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{"sentir","sintamos","sent", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_I | VERB_IMPERATIVE, ""},

{"sentir","sienten","sent", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_HE_SHE_IT, ""},

{"sentir","sientan","sent", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_YOU, ""},

{"tener","tengo","ten", VERB | VERB_PRESENT,PRONOUN_SINGULAR | PRONOUN_I, ""},

{"tener","tienes","ten", VERB | VERB_PRESENT,PRONOUN_SINGULAR | PRONOUN_YOU, ""},

{"tener","tiene","ten", VERB | VERB_PRESENT,PRONOUN_SINGULAR | PRONOUN_HE_SHE_IT, ""},

{"tener","tienen","ten", VERB | VERB_PRESENT,PRONOUN_PLURAL | PRONOUN_HE_SHE_IT, ""},

{"tomar","tome","tom", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU | PRONOUN_HE_SHE_IT | VERB_IMPERATIVE, ""},

{"traducir","traduzco"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"traer","traigo"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"valer","valgo"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"ver","veo"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

// imperfect past

{"estar","estaba","estuv", VERB | VERB_PAST,PRONOUN_SINGULAR | PRONOUN_I, ""}, //yo estuve, tu estuviste, él estuvo, nosotros estuvimos, vosotros estuvisteis, ellos estuvieron

{"estar","estabas","estuv", VERB | VERB_PAST,PRONOUN_SINGULAR | PRONOUN_YOU, ""}, //yo estuve, tu estuviste, él estuvo, nosotros estuvimos, vosotros estuvisteis, ellos estuvieron

{"estar","estuvimos","estuv", VERB | VERB_PAST,PRONOUN_PLURAL | PRONOUN_I, ""}, //yo estuve, tu estuviste, él estuvo, nosotros estuvimos, vosotros estuvisteis, ellos estuvieron

{"estar","estuvistereis","estuv", VERB | VERB_PAST,PRONOUN_PLURAL | PRONOUN_YOU, ""}, //yo estuve, tu estuviste, él estuvo, nosotros estuvimos, vosotros estuvisteis, ellos estuvieron

{"estar","estuvieron","estuv", VERB | VERB_PAST,PRONOUN_PLURAL | PRONOUN_HE_SHE_IT, ""}, //yo estuve, tu estuviste, él estuvo, nosotros estuvimos, vosotros estuvisteis, ellos estuvieron

{"estar","estuvo","estuv", VERB | VERB_PAST, PRONOUN_SINGULAR | PRONOUN_HE_SHE_IT, ""}, //yo estuve, tu estuviste, él estuvo, nosotros estuvimos, vosotros estuvisteis, ellos estuvieron

{"ir","iba","ir", VERB | VERB_PAST, PRONOUN_I | PRONOUN_SINGULAR, ""},

{"ir","ibas","ir", VERB | VERB_PAST, PRONOUN_YOU | PRONOUN_SINGULAR, ""}, // ir (to go)

{"ir","ibamos","ir", VERB | VERB_PAST, PRONOUN_PLURAL | PRONOUN_I, ""},

{"ir","ibais","ir", VERB | VERB_PAST, PRONOUN_PLURAL | PRONOUN_YOU, ""},

{"ir","iban","ir", VERB | VERB_PAST, PRONOUN_PLURAL, ""},

{"ser","era","s", VERB | VERB_PAST, PRONOUN_I | PRONOUN_SINGULAR, ""},

{"ser","eras","s", VERB | VERB_PAST, PRONOUN_YOU | PRONOUN_SINGULAR, ""}, // ser (to be)

{"ser","eramos","s", VERB | VERB_PAST, PRONOUN_PLURAL | PRONOUN_I, ""},

{"ser","erais","s", VERB | VERB_PAST, PRONOUN_PLURAL | PRONOUN_YOU, ""},

{"ser","eran","s", VERB | VERB_PAST, PRONOUN_PLURAL, ""},

{"ver",u8"veía","v", VERB | VERB_PAST, PRONOUN_I | PRONOUN_SINGULAR, ""},

{"ver",u8"veías","v", VERB | VERB_PAST, PRONOUN_YOU | PRONOUN_SINGULAR, ""}, // ver (to see)

{"ver",u8"veíamos","v", VERB | VERB_PAST, PRONOUN_PLURAL | PRONOUN_I, ""},

{"ver",u8"veían","v", VERB | VERB_PAST, PRONOUN_PLURAL, ""},

// and some are irregular in all forms present

{"estar","estamos","est", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_I, ""},

{"estar",u8"estáis","est", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_YOU, ""},

{"estar",u8"estás","est", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU, ""},

{"haber","ha"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR , ""},

{"haber","han"," ", VERB | VERB_PRESENT, PRONOUN_PLURAL, ""},

{"haber","has"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU, ""},

{"haber","hay"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR , ""},

{"haber","he"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"haber","hemos"," ", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_I, ""},

{"haber",u8"habéis"," ", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_YOU, ""},

{"hacer",u8"hacía","hic", VERB | VERB_PAST,PRONOUN_SINGULAR | PRONOUN_I, ""}, // most subjects yo hice,

{"hacer",u8"hacíaimos","hic", VERB | VERB_PAST,PRONOUN_PLURAL | PRONOUN_I, ""}, // most subjects yo hice,

{"hacer",u8"hacíain","hic", VERB | VERB_PAST,PRONOUN_PLURAL, ""}, // most subjects yo hice,

{"hacer",u8"hacíais","hic", VERB | VERB_PAST,PRONOUN_PLURAL | PRONOUN_YOU, ""}, // most subjects yo hice,

{"hacer",u8"hacías","hic", VERB | VERB_PAST,PRONOUN_SINGULAR | PRONOUN_YOU, ""}, // most subjects yo hice,

{"ir","va"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR, ""},

{"ir","vais"," ", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_YOU, ""},

{"ir","vamos"," ", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_I, ""},

{"ir","van"," ", VERB | VERB_PRESENT, PRONOUN_PLURAL , ""},

{"ir","vas"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU, ""},

{"ir","voy"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"ser","eres"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU, ""},

{"ser","es"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR, ""},

{"ser","sois"," ", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_YOU, ""},

{"ser","somos"," ", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_I, ""},

{"ser","son"," ", VERB | VERB_PRESENT, PRONOUN_PLURAL, ""},

{"ser","soy"," ", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_I, ""},

// irregular simple future

{"decir",u8"diré","dec", VERB | AUX_VERB_FUTURE, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"decir",u8"dirás","dec", VERB | AUX_VERB_FUTURE, PRONOUN_SINGULAR | PRONOUN_YOU, ""},

{"decir",u8"dirá","dec", VERB | AUX_VERB_FUTURE, PRONOUN_SINGULAR, ""},

{"decir",u8"diremos","dec", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL | PRONOUN_I, ""},

{"decir",u8"diréis","dec", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL | PRONOUN_YOU, ""},

{"decir",u8"dirán","dec", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL, ""},

{"estar",u8"estaré","est", VERB | AUX_VERB_FUTURE, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"estar",u8"estarás","est", VERB | AUX_VERB_FUTURE, PRONOUN_SINGULAR | PRONOUN_YOU, ""},

{"estar",u8"estará","est", VERB | AUX_VERB_FUTURE, PRONOUN_SINGULAR, ""},

{"estar","estaremos","est", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL | PRONOUN_I, ""},

{"estar",u8"estaréis","est", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL | PRONOUN_YOU, ""},

{"estar",u8"estarán","est", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL, ""},

{"hacer",u8"haré","hac", VERB | AUX_VERB_FUTURE, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"hacer",u8"harás","hac", VERB | AUX_VERB_FUTURE, PRONOUN_SINGULAR | PRONOUN_YOU, ""},

{"hacer",u8"hará","hac", VERB | AUX_VERB_FUTURE, PRONOUN_SINGULAR, ""},

{"hacer","haremos","hac", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL | PRONOUN_I, ""},

{"hacer",u8"haréis","hac", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL | PRONOUN_YOU, ""},

{"hacer",u8"harán","eshact", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL, ""},

// irregular conditional future

{"decir",u8"diría","dec", VERB | AUX_VERB_FUTURE, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"decir",u8"dirías","dec", VERB | AUX_VERB_FUTURE, PRONOUN_SINGULAR | PRONOUN_YOU, ""},

{"decir",u8"diríamos","dec", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL | PRONOUN_I, ""},

{"decir",u8"diríais","dec", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL | PRONOUN_YOU, ""},

{"decir",u8"dirían","dec", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL, ""},

{"estar",u8"estaría","est", VERB | AUX_VERB_FUTURE, PRONOUN_SINGULAR | PRONOUN_I, ""},

{"estar",u8"estarías","est", VERB | AUX_VERB_FUTURE, PRONOUN_SINGULAR | PRONOUN_YOU, ""},

{"estar",u8"estaríamos","est", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL | PRONOUN_I, ""},

{"estar",u8"estaríais","est", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL | PRONOUN_YOU, ""},

{"estar",u8"estarían","est", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL, ""},

{ "hacer",u8"haría","hac", VERB | AUX_VERB_FUTURE, PRONOUN_SINGULAR | PRONOUN_I, ""},

{ "hacer",u8"harías","hac", VERB | AUX_VERB_FUTURE, PRONOUN_SINGULAR | PRONOUN_YOU, ""},

{ "hacer",u8"hacíamos","hac", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL | PRONOUN_I, ""},

{ "hacer",u8"haríais","hac", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL | PRONOUN_YOU, ""},

{ "hacer",u8"harían","eshact", VERB | AUX_VERB_FUTURE, PRONOUN_PLURAL, ""},

// irregular past participle

{ "abrir",u8"abierto","abr", VERB | VERB_PAST_PARTICIPLE | ADJECTIVE, 0, ""},

{ "escribir","escrito","escrib", VERB | VERB_PAST_PARTICIPLE | ADJECTIVE, 0, ""},

{ "cubrir",u8"cubierto","abr", VERB | VERB_PAST_PARTICIPLE | ADJECTIVE, 0, ""},

{ "decir",u8"dicho","dec", VERB | VERB_PAST_PARTICIPLE | ADJECTIVE, 0, ""},

{ "hacer",u8"hecho","hac", VERB | VERB_PAST_PARTICIPLE | ADJECTIVE, 0, ""},

{ "leer",u8"leído","leí", VERB | VERB_PAST_PARTICIPLE, 0, ""},

{ "morir",u8"muerto","mor", VERB | VERB_PAST_PARTICIPLE | ADJECTIVE, 0, ""},

{ "poner",u8"puesto","pon", VERB | VERB_PAST_PARTICIPLE | ADJECTIVE, 0, ""},

{ "romper",u8"roto","romp", VERB | VERB_PAST_PARTICIPLE | ADJECTIVE, 0, ""},

{ "satisfacer",u8"satisfecho","satisfac", VERB | VERB_PAST_PARTICIPLE | ADJECTIVE, 0, ""},

{ "ver",u8"visto","v", VERB | VERB_PAST_PARTICIPLE | ADJECTIVE, 0, ""},

// irregular present participle (verb present paticiple)

{ "leer","leyendo","ley", VERB | VERB_PRESENT_PARTICIPLE, 0, ""},

// Irregular imperatives

{ "coger","coja","cog", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "coger","cojamos","cog", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_I | VERB_IMPERATIVE, ""},

{ "coger","cojan","cog", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "coger",u8"cojáis","cog", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "contar","cuente","cont", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "contar","cuenten","cont", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "contar","cuentes","cont", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "contar",u8"cuénta","cont", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "dar","da","d", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "dar","deis","d", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "dar","des","d", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "dar",u8"dáselo","d", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE | PRONOUN_INDIRECTOBJECT | PRONOUN_INDIRECTOBJECT_SINGULAR, ""},

{ "dar",u8"dé","d", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "decir","di","dec", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "girar","gire","gir", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "girar","gires","gir", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "hacer","haz","hac", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "ir","andante","ir", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "ir","vaya","ir", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "ir","vayamos","ir", VERB | VERB_PRESENT, PRONOUN_SINGULAR | PRONOUN_PLURAL | PRONOUN_I | VERB_IMPERATIVE, ""},

{ "ir","vayan","ir", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "ir","vayas","ir", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "ir","ve","ir", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "ir","vete","ir", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "ir",u8"váyase","ir", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "ir",u8"andá","ir", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "ir",u8"vayáis","ir", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_I | VERB_IMPERATIVE, ""},

{ "ir",u8"vámonos","ir", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_I | VERB_IMPERATIVE, ""},

{ "laxar",u8"lávenselas","lax", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE | PRONOUN_OBJECT_PLURAL | PRONOUN_OBJECT_SINGULAR, ""},

{ "poner","pon","pon", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "repetir","repite","repit", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "separar","separa","separ", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_I | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "saltar","salte","sal", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_I | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "ser",u8"sé","ser", VERB | VERB_PRESENT | SINGULAR_PERSON,PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "tener","tenga","ten", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "tener","tengamos","ten", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_I | VERB_IMPERATIVE, ""},

{ "tener","tengan","ten", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "tener","tengas","ten", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "tener",u8"tengáis","ten", VERB | VERB_PRESENT, PRONOUN_PLURAL | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "tenir","ten","ten", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

{ "venir","ven","ven", VERB | VERB_PRESENT | SINGULAR_PERSON, PRONOUN_SINGULAR | PRONOUN_YOU | VERB_IMPERATIVE, ""},

// sentinal

{ "", NULL, NULL, 0, 0, ""},

};

void MarkSpanishTags(WORDP OL, int i)

{ // we have to manual name concept because primary naming is from the english corresponding bit

uint64 systemFlags = GetSystemFlags(OL);

if (finalPosValues[i] & PRONOUN_OBJECT) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_object")), i, i, CANONICAL);

if (systemFlags & PRONOUN_SINGULAR) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_singular")), i, i, CANONICAL);

if (systemFlags & PRONOUN_PLURAL) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_plural")), i, i, CANONICAL);

if (systemFlags & PRONOUN_I) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_i")), i, i, CANONICAL);

if (systemFlags & PRONOUN_YOU) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_you")), i, i, CANONICAL);

if (systemFlags & PRONOUN_HE_SHE_IT) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_he_she_it")), i, i, CANONICAL);

if (systemFlags & PRONOUN_OBJECT_SINGULAR) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_object_singular")), i, i, CANONICAL);

if (systemFlags & PRONOUN_OBJECT_PLURAL) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_object_plural")), i, i, CANONICAL);

if (systemFlags & PRONOUN_OBJECT_I) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_object_i")), i, i, CANONICAL);

if (systemFlags & PRONOUN_OBJECT_YOU) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_object_you")), i, i, CANONICAL);

if (systemFlags & PRONOUN_OBJECT_HE_SHE_IT) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_object_he_she_it")), i, i, CANONICAL);

if (systemFlags & PRONOUN_INDIRECTOBJECT) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_indirectobject")), i, i, CANONICAL);

if (systemFlags & PRONOUN_INDIRECTOBJECT_SINGULAR) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_indirectobject_singular")), i, i, CANONICAL);

if (systemFlags & PRONOUN_INDIRECTOBJECT_PLURAL) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_indirectobject_plural")), i, i, CANONICAL);

if (systemFlags & PRONOUN_INDIRECTOBJECT_I) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_indirectobject_i")), i, i, CANONICAL);

if (systemFlags & PRONOUN_INDIRECTOBJECT_YOU) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_indirectobject_you")), i, i, CANONICAL);

if (systemFlags & PRONOUN_INDIRECTOBJECT_HE_SHE_IT) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~pronoun_indirectobject_he_she_it")), i, i, CANONICAL);

if (finalPosValues[i] & AUX_VERB_FUTURE)

{

MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~AUX_VERB_FUTURE")), i, i, CANONICAL);

MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~SPANISH_FUTURE")), i, i, CANONICAL);

MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~verb_future")), i, i, CANONICAL);

}

if (allOriginalWordBits[i] & NOUN_HE)

{

MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~NOUN_HE")), i, i, CANONICAL);

MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~SPANISH_HE")), i, i, CANONICAL);

}

if (allOriginalWordBits[i] & NOUN_SHE)

{

MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~NOUN_SHE")), i, i, CANONICAL);

MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~SPANISH_SHE")), i, i, CANONICAL);

}

if (allOriginalWordBits[i] & SINGULAR_PERSON) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~SINGULAR_PERSON")), i, i, CANONICAL);

if (systemFlags & VERB_IMPERATIVE) MarkMeaningAndImplications(0, 0, MakeMeaning(StoreWord("~verb_imperative")), i, i, CANONICAL);

}

uint64 GetSpanishLemmaBits(char* wordx)

{

WORDP D = FindWord(wordx, 0, PRIMARY_CASE_ALLOWED,true);

if (!D) return 0;

WORDP E = RawCanonical(D);

if (!E || *E->word != '`') return 0; // normal english canonical or simple canonical of foreign (not multiple choice)

uint64 properties = D->properties;

char word[MAX_WORD_SIZE];

char type[MAX_WORD_SIZE];

strcpy(word, E->word + 1);

char* lemma = word;

char* tags = strrchr(word, '`');

*tags++ = 0; // type decriptors

// walk list of pos tags and simultaneously walk the list of lemmas

while (*tags && (tags = ReadCompiledWord(tags, type)))

{

char ptag[MAX_WORD_SIZE];

sprintf(ptag, "_%s", type);

WORDP X = FindWord(ptag,0,PRIMARY_CASE_ALLOWED,true);

if (X) properties |= X->properties;

tags = SkipWhitespace(tags);

}

return properties;

}

uint64 FindSpanishSingular(char* original, char* word, WORDP& entry, WORDP& canonical, uint64& sysflags)

{

WORDP E = FindWord(word,0,PRIMARY_CASE_ALLOWED,true);

if (E && E->properties & NOUN)

{

canonical = E;

if (!exportdictionary)

{

entry = GetLanguageWord(original);

}

else entry = canonical;

sysflags = E->systemFlags;

return NOUN | NOUN_PLURAL;

}

return 0;

}

uint64 KnownSpanishUnaccented(char* original, WORDP& entry, uint64& sysflags)

{

char word[MAX_WORD_SIZE];

MakeLowerCopy(word, original);

char copy[MAX_WORD_SIZE];

char* at = word - 1;

char c;

//with the marks over the five vowels(á, é, í, ó, ú), you will never see two of those in the same word.

while ((c = *++at)) // try single accented change

{

char* change = NULL;

if (c == 'a') change = "\xC3\xA1";

else if (c == 'e') change = "\xC3\xA9";

else if (c == 'i') change = "\xC3\xAD";

else if (c == 'o') change = "\xC3\xB3";

else if (c == 'u') change = "\xC3\xBA";

if (change)

{

strcpy(copy, word);

strcpy(copy + (at - word), change);

strcpy(copy + (at - word) + 2, at + 1);

WORDP canonical = NULL;

uint64 newSysflags = 0;

uint64 properties = ComputeSpanish1(2, copy, entry, canonical, newSysflags);

if (properties)

{

sysflags |= newSysflags;

return properties;

}

}

}

return 0;

}

static WORDP ConfirmSpanishInfinitive(char* stem, char* verbType, int stemLen, char* original, const char* suffix, char* rawlemma = NULL);

static WORDP ConfirmSpanishInfinitive(char* stem, char* verbType, int stemLen, char* original, const char* suffix, char* rawlemma)

{

char word[MAX_WORD_SIZE];

strcpy(word, stem);

char rawword[MAX_WORD_SIZE];

if (rawlemma) strcpy(rawword, rawlemma);

else strcpy(rawword, stem);

WORDP Lemma;

if (*verbType) // we know the kind of verb

{

strcpy(word + stemLen, verbType); // make lemma from stem and type

Lemma = FindWord(word,0,PRIMARY_CASE_ALLOWED,true);

if (Lemma && Lemma->properties & VERB) // this is a lemma

{

strcpy(rawword + stemLen, suffix); // the actual word we would generate

if (!stricmp(rawword, original))

return Lemma; // we would get this

}

}

else // try all 3 verb types

{

strcpy(word + stemLen, "er"); // papxxx becomes paper

Lemma = FindWord(word,0, PRIMARY_CASE_ALLOWED,true);

if (Lemma && Lemma->properties & VERB)

{

strcpy(rawword + stemLen, suffix); // the actual

if (!stricmp(rawword, original))

return Lemma; // we would get this

}

strcpy(word + stemLen, "ar");

Lemma = FindWord(word, 0, PRIMARY_CASE_ALLOWED, true);

if (Lemma && Lemma->properties & VERB)

{

strcpy(rawword + stemLen, suffix); // the actual

if (!stricmp(rawword, original))

return Lemma; // we would get this

}

strcpy(word + stemLen, "ir");

Lemma = FindWord(word, 0, PRIMARY_CASE_ALLOWED, true);

if (Lemma && Lemma->properties & VERB)

{

strcpy(rawword + stemLen, suffix); // the actual

if (!stricmp(rawword, original))

return Lemma; // we would get this

}

}

return NULL;

}

static uint64 FindSpanishInfinitive(char* original, const char* suffix, char* verbType, WORDP& entry, WORDP& canonical, uint64& sysflags)

{

// Infinitives always end in ar, er or ir added to the stem - verbType names this suffix.

// If empty, means try all 3 types

// Conjugation involves changing to different suffix on stem verb

// So, given original and a suffix to consider, we know the stem part before that suffix.

// Of course the stem may have changed spelling along the way, for added complexity.

uint64 properties = 0;

size_t originalLen = strlen(original);

size_t suffixLen = strlen(suffix);

size_t stemLen = originalLen - suffixLen;

if (strcmp(original + stemLen, suffix)) return 0; // this conjugation doesnt end with suffix named

WORDP D = GetLanguageWord(original);

// original ended in designated suffix. See if we can get its infinitive form with no changes of spelling

char stem[MAX_WORD_SIZE];

strncpy(stem, original, stemLen);

char lemma[MAX_WORD_SIZE];

stem[stemLen] = 0;

strcpy(lemma, stem);

WORDP oldcanonical = canonical;

canonical = ConfirmSpanishInfinitive(stem, verbType, stemLen, original, suffix);

if (canonical && canonical->properties & (VERB_INFINITIVE | NOUN_GERUND)) // simple verb conjugation matched. we have canonical also.

{

entry = D;

return VERB_INFINITIVE;

}

// didnt have direct match, but sometimes stem changes spelling

// if from pronoun, may have to remove added accent

char lemma1[MAX_WORD_SIZE];

strcpy(lemma1, stem);

char c = 'a';

char* found = strstr(lemma1, "\xC3\xA1");

if (!found) { found = strstr(lemma1, "\xC3\xA9"); c = 'e'; }

if (!found) { found = strstr(lemma1, "\xC3\xAD"); c = 'i'; }

if (!found) { found = strstr(lemma1, "\xC3\xB3"); c = 'o'; }

if (!found) { found = strstr(lemma1, "\xC3\xBA"); c = 'u'; }

if (!canonical && found) // replace accented form with unaccented

{

*found = c;

memmove(found + 1, found + 2, strlen(found + 1)); // know its 2 chars wide

canonical = ConfirmSpanishInfinitive(lemma1, verbType, stemLen, original, suffix);

if (canonical) // simple verb conjugation matched. we have canonical also.

{

entry = D;

return properties;

}

}

strcpy(lemma1, stem);

strcat(lemma1, suffix);

if (properties & AUX_VERB_FUTURE)

{

canonical = FindWord(stem,0,PRIMARY_CASE_ALLOWED,true);

if (canonical && canonical->properties & VERB && !stricmp(lemma1, original)) { ; }

else canonical = NULL;

}

// stem changed from e to ie

strcpy(lemma1, stem);

char* change = strstr(lemma1, "ie");

char* again = (change) ? strstr(change + 1, "ie") : NULL;

if (again) change = again; // prefer 2nd one

if (!canonical && change) // ie from e

{

memmove(change, change + 1, strlen(change));

canonical = ConfirmSpanishInfinitive(lemma1, verbType, stemLen, original, suffix, stem);

}

// stem changed from o to ue

strcpy(lemma1, stem);

change = strstr(lemma1, "ue");

again = (change) ? strstr(change + 1, "ue") : NULL;

if (!canonical && change) // ue from o

{

memmove(change, change + 1, strlen(change));

*change = 'o';

canonical = ConfirmSpanishInfinitive(lemma1, verbType, stemLen, original, suffix, stem);

}

// stem changed from e to i

if (!strcmp(verbType, "ir")) // ir verb i from e

{

strcpy(lemma1, stem);

char* change = strrchr(lemma1, 'i');

if (!canonical && change) // i from e

{

*change = 'e';

canonical = ConfirmSpanishInfinitive(lemma1, verbType, stemLen, original, suffix, stem);

}

}

else if (!stricmp(verbType, "er"))

{

strcpy(lemma1, stem);

char* change = strstr(lemma1, "ie");

char* again = (change) ? strstr(change + 1, "ie") : NULL;

if (again) change = again;

if (!canonical && change) // ie from e

{

memmove(change, change + 1, strlen(change));

canonical = ConfirmSpanishInfinitive(lemma1, verbType, stemLen, original, suffix, stem);

}

// stem o changed to ue

strcpy(lemma1, stem);

change = strstr(lemma1, "ue");

again = (change) ? strstr(change + 1, "ue") : NULL;

if (!canonical && change) // ue from o

{

memmove(change, change + 1, strlen(change));

*change = 'o';

canonical = ConfirmSpanishInfinitive(lemma1, verbType, stemLen, original, suffix, stem);

}

}

// stem changed from c to b (hacer conditional)

strcpy(lemma1, stem);

change = strrchr(lemma1, 'b');

if (!canonical && change) // b from c

{

memmove(change, change + 1, strlen(change));

*change = 'c';

canonical = ConfirmSpanishInfinitive(lemma1, verbType, stemLen, original, suffix, stem);

}

// IRREGULAR VERB SPECIALS

//

// stem changed from c to r (hacer future)

strcpy(lemma1, stem);

change = strstr(lemma1, "r");

if (!canonical && change && properties & AUX_VERB_FUTURE) // r from c

{

memmove(change, change + 1, strlen(change));

*change = 'c';

canonical = ConfirmSpanishInfinitive(lemma1, verbType, stemLen, original, suffix, stem);

*change = 'r'; // revert

}

if (canonical)

{// since we found infinitive for it, assign info to the word

entry = D;

return properties | (canonical->properties & VERB_BITS);

}

if (!canonical) canonical = oldcanonical;

return properties;

}

static uint64 ReflexiveVerbSpanish(char* word, WORDP& entry, WORDP& canonical, uint64& sysflags)

{

uint64 properties = 0;

size_t len = strlen(word);

// try reflexive forms of any regular verb

if (len > 2 && word[len - 2] == 's' && word[len - 1] == 'e')

{

char base[MAX_WORD_SIZE];

strcpy(base, word);

base[len - 2] = 0;

WORDP E = FindWord(base,0,PRIMARY_CASE_ALLOWED,true);

if (E && E->properties & VERB)

{

canonical = E;

if (!exportdictionary)

{

entry = GetLanguageWord(word);

properties |= VERB_PRESENT;

}

else entry = canonical;

sysflags |= PRONOUN_REFLEXIVE;

// if (E->properties & VERB_INFINITIVE) RemoveProperty(E, VERB_INFINITIVE); // treetagger lied - direct change, not restorable

properties |= VERB_PRESENT; // treetagger lied - direct change, not restorable

// if (entry->properties & VERB_INFINITIVE) RemoveProperty(entry, VERB_INFINITIVE); // treetagger lied - direct change, not restorable

properties |= E->properties;

}

}

return properties;

}

static void MakeUnaccentedCopy(const char* word, char* copy)

{

struct AccentEquivalence {

const char accent[3];

const char unaccent;

};

const AccentEquivalence table[] = {

{ "\xC3\xA1", 'a' },

{ "\xC3\xA9", 'e' },

{ "\xC3\xAD", 'i' },

{ "\xC3\xB3", 'o' },

{ "\xC3\xBA", 'u' }

};

while (*word) {

bool changed_letter = false;

if (*word == '\xC3')

{

for (const AccentEquivalence& entry : table) {

if (entry.accent[1] == word[1]) {

*copy = entry.unaccent;

changed_letter = true;

}

}

}

if (changed_letter) {

word += 2;

}

else {

*copy = *word;

word++;

}

copy++;

}

*copy = '\0';

}

static uint64 IrregularSpanishVerb(char* wordToFind, WORDP& entry, WORDP& canonical, uint64& sysflags)

{

uint64 properties = 0;

// All searches done on unaccented version

char unaccentedWord[MAX_WORD_SIZE];

static unordered_map<std::string, IrregularSpanishInfo*> verb_map;

if (verb_map.empty()) {

IrregularSpanishInfo* entry = irregularSpanishVerbs;

while (entry->lemma[0] != '\0') {

MakeUnaccentedCopy(entry->original, unaccentedWord);

if (verb_map.find(unaccentedWord) != verb_map.end()) {

printf("Error: duplicate original %s unaccented %s\n",

entry->original, unaccentedWord);

}

verb_map[unaccentedWord] = entry;

entry->unaccented = unaccentedWord;

entry++;

}

}

MakeUnaccentedCopy(wordToFind, unaccentedWord);

if (verb_map.find(unaccentedWord) != verb_map.end())

{

IrregularSpanishInfo* fn = verb_map[unaccentedWord];

canonical = GetLanguageWord(fn->lemma);

sysflags |= fn->sysFlags;

properties = fn->properties;

}

return properties;

}

static WORDP FindSpanishWordRemoveAccent(char* base)

{

WORDP D = FindWord(base,0,PRIMARY_CASE_ALLOWED,true);

if (D) return D;

char copy[MAX_WORD_SIZE];

strcpy(copy, base);

char* ptr = copy - 1;

char c = 0;

while (*++ptr)

{

if (!strnicmp(ptr, "\xC3\xA1", 2)) c = 'a';

else if (!strnicmp(ptr, "\xC3\xA9", 2)) c = 'e';

else if (!strnicmp(ptr, "\xC3\xAD", 2)) c = 'i';

else if (!strnicmp(ptr, "\xC3\xB3", 2)) c = 'o';

else if (!strnicmp(ptr, "\xC3\xBA", 2)) c = 'u';

if (c)

{

*ptr = c;

memmove(ptr + 1, ptr + 2, strlen(ptr + 1));

D = FindWord(copy,0,PRIMARY_CASE_ALLOWED,true);

if (D) strcpy(base, copy);

return D;

}

}

return NULL;

}

WORDP FindSpanishWord(char* base, char* full)

{ // presume it had accent added, try to remove it

WORDP D = FindWord(full, 0, PRIMARY_CASE_ALLOWED, true); // dictionary knows it?

if (D)

{

D = GetCanonical(D, VERB_INFINITIVE);

if (D && D->properties & VERB_INFINITIVE) return D;

}

return FindSpanishWordRemoveAccent(base);

}

uint64 ImperativeSpanish(char* word, WORDP& entry, WORDP& canonical, uint64& sysflags)

{

char base[MAX_WORD_SIZE];

strcpy(base, word);

size_t len = strlen(base);

WORDP Dbase = FindSpanishWordRemoveAccent(base);

uint64 properties = 0;

if (Dbase)

{

entry = Dbase;

}

// tu form, add 'r' to form infinitive

strcat(base, "r");

WORDP Dcanon = FindSpanishWord(base, base);

if (Dcanon && (Dcanon->properties & VERB_INFINITIVE))

{

canonical = Dcanon;

sysflags |= PRONOUN_YOU | PRONOUN_SINGULAR | VERB_IMPERATIVE;

return properties | VERB;

}

base[len] = '\0';

// vosotros/vosotras form, remove 'd' and add 'r' to form infinitive

// also, éis -> ar as infinitive,

if (base[len - 1] == 'd') {

base[len - 1] = 'r';

Dcanon = FindSpanishWord(base, base);

if (Dcanon && (Dcanon->properties & VERB_INFINITIVE))

{

canonical = Dcanon;

sysflags |= PRONOUN_YOU | PRONOUN_PLURAL | VERB_IMPERATIVE;

return properties | VERB;

}

base[len - 1] = 'd';

}

if (!stricmp(&base[len - 4], u8"éis")) {

strcpy(&base[len - 4], "ar");

Dcanon = FindSpanishWord(base, base);

if (Dcanon && (Dcanon->properties & VERB_INFINITIVE))

{

canonical = Dcanon;

sysflags |= PRONOUN_YOU | PRONOUN_SINGULAR | VERB_IMPERATIVE;

return properties | VERB;

}

strcpy(&base[len - 4], u8"éis");

}

// usted form, e -> ar as infinitive, a -> er, a -> ir

if (base[len - 1] == 'e') {

strcpy(&base[len - 1], "ar");

Dcanon = FindSpanishWord(base, base);

if (Dcanon && (Dcanon->properties & VERB_INFINITIVE))

{

canonical = Dcanon;

sysflags |= PRONOUN_YOU | PRONOUN_SINGULAR | VERB_IMPERATIVE;

return properties | VERB;

}

strcpy(&base[len - 1], "e");

}

if (base[len - 1] == 'a') {

strcpy(&base[len - 1], "er");

Dcanon = FindSpanishWord(base, base);

if (Dcanon && (Dcanon->properties & VERB_INFINITIVE))

{

canonical = Dcanon;

sysflags |= PRONOUN_YOU | PRONOUN_SINGULAR | VERB_IMPERATIVE;

return properties | VERB;

}

strcpy(&base[len - 1], "ir");

Dcanon = FindSpanishWord(base, base);

if (Dcanon && (Dcanon->properties & VERB_INFINITIVE))

{

canonical = Dcanon;

sysflags |= PRONOUN_YOU | PRONOUN_SINGULAR | VERB_IMPERATIVE;

return properties | VERB;

}

strcpy(&base[len - 1], "a");

}

// ustedes form, en -> ar as infinitive, an -> er, an -> ir

if (!stricmp(&base[len - 2], "en"))

{

strcpy(&base[len - 2], "ar");

Dcanon = FindSpanishWord(base, base);

if (Dcanon && (Dcanon->properties & VERB_INFINITIVE))

{

canonical = Dcanon;

sysflags |= PRONOUN_YOU | PRONOUN_PLURAL | VERB_IMPERATIVE;

return properties | VERB;

}

strcpy(&base[len - 2], "en");

}

if (!stricmp(&base[len - 2], "an")) {

strcpy(&base[len - 2], "er");

Dcanon = FindSpanishWord(base, base);

if (Dcanon && (Dcanon->properties & VERB_INFINITIVE))

{

canonical = Dcanon;

sysflags |= PRONOUN_YOU | PRONOUN_PLURAL | VERB_IMPERATIVE;

return properties | VERB;

}

strcpy(&base[len - 2], "ir");

Dcanon = FindSpanishWord(base, base);

if (Dcanon && (Dcanon->properties & VERB_INFINITIVE))

{

canonical = Dcanon;

sysflags |= PRONOUN_YOU | PRONOUN_PLURAL | VERB_IMPERATIVE;

return properties | VERB;

}

strcpy(&base[len - 2], "an");

}

// nosotros form, emos -> ar as infinitive, amos -> er an ir

if (!stricmp(&base[len - 4], "emos")) {

strcpy(&base[len - 4], "ar");

Dcanon = FindSpanishWord(base, base);

if (Dcanon && (Dcanon->properties & VERB_INFINITIVE))

{

canonical = Dcanon;

sysflags |= PRONOUN_I | PRONOUN_PLURAL | VERB_IMPERATIVE;

return properties | VERB;

}

strcpy(&base[len - 4], "emos");

}

if (!stricmp(&base[len - 4], "amos")) {

strcpy(&base[len - 4], "er");

Dcanon = FindSpanishWord(base, base);

if (Dcanon && (Dcanon->properties & VERB_INFINITIVE))

{

canonical = Dcanon;

sysflags |= PRONOUN_I | PRONOUN_PLURAL | VERB_IMPERATIVE;

return properties | VERB;

}

strcpy(&base[len - 4], "ir");

Dcanon = FindSpanishWord(base, base);

if (Dcanon && (Dcanon->properties & VERB_INFINITIVE))

{

canonical = Dcanon;

sysflags |= PRONOUN_I | PRONOUN_PLURAL | VERB_IMPERATIVE;

return properties | VERB;

}

strcpy(&base[len - 4], "amos");

}

// irregular form

base[len] = '\0';

uint64 transient = IrregularSpanishVerb(base, entry, canonical, sysflags);

if (sysflags & VERB_IMPERATIVE) return properties | transient;

return false;

}

uint64 PresentSpanish(char* original, WORDP& entry, WORDP& canonical, uint64& sysflags)

{

uint64 properties = PRONOUN_SUBJECT | VERB_PRESENT | VERB;

// imperative tu form? parar(to stop) = paras(you stop) → ¡Para!(Stop!)

uint64 transient = 0;

uint64 ans = ImperativeSpanish(original, entry, canonical, transient);

if (ans)

{

sysflags |= transient;

return properties | ans;

}

// we have the original. We know verb infinitive comes in 3 flavors. We try those flavors with the

// various possible stems.

// Spanish infinitives end in ar, er, or ir.

//

// 1st person // yo (habl)o (com)o (abr)o

transient = PRONOUN_SINGULAR | PRONOUN_I;

if (FindSpanishInfinitive(original, "o", "ar", entry, canonical, transient)) // yo

{

sysflags |= transient;

return properties;

}

else if (FindSpanishInfinitive(original, "o", "er", entry, canonical, transient)) /// él, ella, usted habl + a habla

{

sysflags |= transient;

return properties;

}

else if (FindSpanishInfinitive(original, "o", "ir", entry, canonical, transient))

{

sysflags |= transient;

return properties;

}

// 2nd person // tú (habl)as (com)es (abr)es

transient = PRONOUN_SINGULAR | PRONOUN_YOU;

if (FindSpanishInfinitive(original, "as", "ar", entry, canonical, transient)) // tu

{

sysflags |= transient;

return properties;

}

else if (FindSpanishInfinitive(original, "es", "er", entry, canonical, transient))

{

sysflags |= transient;

return properties;

}

else if (FindSpanishInfinitive(original, "es", "ir", entry, canonical, transient))

{

sysflags |= transient;

return properties;

}

// 3rd person // él / ella (habl)a (com)e (abr)e

transient = PRONOUN_SINGULAR;

if (FindSpanishInfinitive(original, "a", "ar", entry, canonical, transient)) /// él, ella, usted habl + a habla

{

sysflags |= transient;

return properties;

}

else if (FindSpanishInfinitive(original, "e", "er", entry, canonical, transient))

{

sysflags |= transient;

return properties;

}

else if (FindSpanishInfinitive(original, "e", "ir", entry, canonical, transient))

{

sysflags |= transient;

return properties;

}

transient = PRONOUN_PLURAL | PRONOUN_I;

// 1st person plural // nosotros (habl)amos (com)emos (abr)imos

if (FindSpanishInfinitive(original, "amos", "ar", entry, canonical, transient)) /// él, ella, usted habl + a habla

{

sysflags |= transient;

return properties;

}

else if (FindSpanishInfinitive(original, "emos", "er", entry, canonical, transient))

{

sysflags |= transient;

return properties;

}

else if (FindSpanishInfinitive(original, "imos", "ir", entry, canonical, transient))

{

sysflags |= transient;

return properties;

}

transient = PRONOUN_PLURAL | PRONOUN_YOU;

// 2nd person plural // vosotros (habl)áis (com)éis (abr)ís

if (FindSpanishInfinitive(original, u8"áis", "ar", entry, canonical, transient)) /// él, ella, usted habl + a habla

{

sysflags |= transient;

return properties;

}

else if (FindSpanishInfinitive(original, u8"áis", "er", entry, canonical, transient))

{

sysflags |= transient;

return properties;

}

else if (FindSpanishInfinitive(original, u8"ís", "ir", entry, canonical, transient))

{

sysflags |= transient;

return properties;

}

transient = PRONOUN_PLURAL;

// 3rd person plural ellos, ellas, ustedes // ellos/ellas (habl)an (com)en (abr)en

if (FindSpanishInfinitive(original, "an", "ar", entry, canonical, transient))

{

sysflags |= transient;

return properties;

}

else if (FindSpanishInfinitive(original, "en", "er", entry, canonical, transient))

{

sysflags |= transient;

return properties;

}

else if (FindSpanishInfinitive(original, "en", "ir", entry, canonical, transient))

{

sysflags |= transient;

return properties;

}

return 0;

}

uint64 PastSpanish(char* original, WORDP& entry, WORDP& canonical, uint64& sysflags)

{

// FindSpanishInfinitive(original, suffix, verb type, etnry, canonical, properties so far, new properties if match ) // yo

uint64 properties = PRONOUN_SUBJECT | VERB_PAST | VERB;

// 1st person preterite past // yo (habl)é (com)í (abr)í

uint64 transient = PRONOUN_SINGULAR | PRONOUN_I;