// copy constructor
//Type Position Attribute Qualifier PersonDegree PersonGender PersonNumber Mood Lemma Root SpecialGroup
public WordPartGrammar(WordPartGrammar grammar)
{
if (grammar != null)
{
this.word_part = grammar.WordPart;
this.type = grammar.Type;
this.position = grammar.Position;
this.attribute = grammar.Attribute;
this.qualifier = grammar.Qualifier;
this.person_degree = grammar.PersonDegree;
this.person_gender = grammar.PersonGender;
this.person_number = grammar.PersonNumber;
this.mood = grammar.Mood;
this.lemma = grammar.Lemma;
this.root = grammar.Root;
this.special_group = grammar.SpecialGroup;
}
}
//Type Position Attribute Qualifier PersonDegree PersonGender PersonNumber Mood Lemma Root SpecialGroup
// copy constructor
public WordPartGrammar(WordPartGrammar grammar)
{
if (grammar != null)
{
this.word_part = grammar.WordPart;
this.type = grammar.Type;
this.position = grammar.Position;
this.attribute = grammar.Attribute;
this.qualifier = grammar.Qualifier;
this.person_degree = grammar.PersonDegree;
this.person_gender = grammar.PersonGender;
this.person_number = grammar.PersonNumber;
this.mood = grammar.Mood;
this.lemma = grammar.Lemma;
this.root = grammar.Root;
this.special_group = grammar.SpecialGroup;
}
}
//Type Position Attribute Qualifier PersonDegree PersonGender PersonNumber Mood Lemma Root SpecialGroup
// instance constructor
public WordPartGrammar(WordPart word_part, List<string> grammar)
{
if (word_part != null)
{
this.word_part = word_part;
if (grammar != null)
{
if (grammar.Count > 1)
{
this.type = grammar[0];
switch (this.type)
{
case "PREFIX":
{
//Al+
//bi+
//bip+
//ka+
//ta+
//sa+
//ya+
//ha+
//A_INTG+
//A_EQ+"
//b_PART+
//f_REM+
//f_CONJ+
//f_RSLT+
//f_SUP+
//f_CAUS+
//l_PP+
//l_EMPH+
//l_PRP+
//l_IMPV+
//w_CONJ+
//w_REM+
//w_CIRC+
//w_SUP+
//w_PP+
//w_COM+
if (grammar.Count == 2)
{
this.position = grammar[1];
}
else
{
throw new Exception("WordPartGrammar: Invalide PREFIX at word part " + word_part.Address);
}
}
break;
case "STEM":
{
for (int i = 1; i < grammar.Count; i++)
{
string[] parts = grammar[i].Split(':');
if (parts.Length == 2)
{
if (parts[0] == "POS")
{
//INL
//N
//PN
//V
//ADJ
//IMPN
//AC
//AMD
//ANS
//AVR
//CERT
//COND
//EXH
//EXL
//EXP
//FUT
//INC
//INT
//INTG
//NEG
//PREV
//PRO
//RES
//RET
//SUP
//SUR
//PP
//CONJ
//SUB
//EQ
//REM
//CIRC
//COM
//RSLT
//CAUS
//EMPH
//PRP
//IMPV
//PRON
//DEM
//REL
//T
//LOC
this.position = parts[1];
}
else if (parts[0] == "LEM")
{
this.lemma = parts[1];
}
else if (parts[0] == "ROOT")
{
this.root = parts[1];
}
else if (parts[0] == "SP")
{
this.special_group = parts[1];
}
else if (parts[0] == "MOOD")
{
this.mood = parts[1];
}
else
{
throw new Exception("WordPartGrammar: Invalide STEM at word part " + word_part.Address);
}
}
else if (parts.Length == 1) // attribute or qualifier
{
switch (parts[0])
{
case "1":
case "2":
case "3":
this.person_degree = parts[0][0].ToString();
break;
case "M":
case "F":
this.person_gender = parts[0][0].ToString();
break;
case "S":
case "D":
case "P":
this.person_number = parts[0][0].ToString();
break;
case "1M":
case "2M":
case "3M":
case "1F":
case "2F":
case "3F":
this.person_degree = parts[0][0].ToString();
this.person_gender = parts[0][1].ToString();
break;
case "1S":
case "2S":
case "3S":
case "1D":
case "2D":
case "3D":
case "1P":
case "2P":
case "3P":
this.person_degree = parts[0][0].ToString();
this.person_number = parts[0][1].ToString();
break;
case "MS":
case "FS":
case "MD":
case "FD":
case "MP":
case "FP":
this.person_gender = parts[0][0].ToString();
this.person_number = parts[0][1].ToString();
break;
case "1MS":
case "2MS":
case "3MS":
case "1FS":
case "2FS":
case "3FS":
case "1MD":
case "2MD":
case "3MD":
case "1FD":
case "2FD":
case "3FD":
case "1MP":
case "2MP":
case "3MP":
case "1FP":
case "2FP":
case "3FP":
this.person_degree = parts[0][0].ToString();
this.person_gender = parts[0][1].ToString();
this.person_number = parts[0][2].ToString();
break;
default:
if (String.IsNullOrEmpty(this.attribute))
{
//VN
//ACT_PCPL
//PASS_PCPL
//NOM
//ACC
//GEN
//DEF
//INDEF
//PERF
//IMPF
//IMPV
this.attribute = parts[0];
}
else
{
//NOM
//ACC
//ACT
//PASS
//(I)
//(II)
//(III)
//(IV)
//(V)
//(VI)
//(VII)
//(VIII)
//(IX)
//(X)
//(XI)
//(XII)
this.qualifier = parts[0];
}
break;
}
}
}
}
break;
case "SUFFIX":
{
if (grammar.Count == 2)
{
//SUFFIX|+n_EMPH
//SUFFIX|+VOC
//SUFFIX|+l_PP
//SUFFIX|+PRON:2MP
//SUFFIX|+A_SILENT
string[] parts = grammar[1].Split(':');
if (parts.Length == 1)
{
this.position = parts[0];
}
else if (parts.Length == 2)
{
if (parts[0] == "+PRON")
{
this.position = parts[0];
if (parts[1].Length == 3)
{
this.person_degree = parts[1][0].ToString();
this.person_gender = parts[1][1].ToString();
this.person_number = parts[1][2].ToString();
}
else if (parts[1].Length == 2)
{
if ((parts[1][0] == '1') || (parts[1][0] == '2') || (parts[1][0] == '3'))
{
this.person_degree = parts[1][0].ToString();
}
else if ((parts[1][0] == 'M') || (parts[1][0] == 'F'))
{
this.person_gender = parts[1][0].ToString();
}
else if ((parts[1][0] == 'S') || (parts[1][0] == 'D') || (parts[1][0] == 'P'))
{
this.person_number = parts[1][0].ToString();
}
if ((parts[1][1] == 'M') || (parts[1][1] == 'F'))
{
this.person_gender = parts[1][1].ToString();
}
else if ((parts[1][1] == 'S') || (parts[1][1] == 'D') || (parts[1][1] == 'P'))
{
this.person_number = parts[1][1].ToString();
}
}
else if (parts[1].Length == 1)
{
if ((parts[1][0] == '1') || (parts[1][0] == '2') || (parts[1][0] == '3'))
{
this.person_degree = parts[1][0].ToString();
}
else if ((parts[1][0] == 'M') || (parts[1][0] == 'F'))
{
this.person_gender = parts[1][0].ToString();
}
else if ((parts[1][0] == 'S') || (parts[1][0] == 'D') || (parts[1][0] == 'P'))
{
this.person_number = parts[1][0].ToString();
}
}
}
else
{
throw new Exception("WordPartGrammar: SUFFIX|+PRON expected at word part " + word_part.Address);
}
}
else
{
throw new Exception("WordPartGrammar: Invalide SUFFIX at word part " + word_part.Address);
}
}
else
{
throw new Exception("WordPartGrammar: Invalide SUFFIX at word part " + word_part.Address);
}
}
break;
default:
break;
}
}
}
}
}
// corpus word parts from http://corpus.quran.com version 0.4 - modified by Ali Adams
public static void LoadWordParts(Book book)
{
if (book != null)
{
string filename = Globals.DATA_FOLDER + "/" + "word-parts.txt";
if (File.Exists(filename))
{
using (StreamReader reader = File.OpenText(filename))
{
int waw_count = 0;
int previous_verse_number = 0;
while (!reader.EndOfStream)
{
try
{
string line = reader.ReadLine();
if ((line.Length == 0) || line.StartsWith("#") || line.StartsWith("LOCATION") || line.StartsWith("ADDRESS"))
{
continue; // skip header info
}
else
{
string[] parts = line.Split('\t');
if (parts.Length >= 4)
{
string address = parts[0];
if (address.StartsWith("(") && address.EndsWith(")"))
{
address = parts[0].Substring(1, parts[0].Length - 2);
}
string[] address_parts = address.Split(':');
if (address_parts.Length == 4)
{
int chapter_number = int.Parse(address_parts[0]);
int verse_number = int.Parse(address_parts[1]);
if (previous_verse_number != verse_number)
{
waw_count = 0;
previous_verse_number = verse_number;
}
int word_number = int.Parse(address_parts[2]) + waw_count;
int word_part_number = int.Parse(address_parts[3]);
string buckwalter = parts[1];
string tag = parts[2];
Chapter chapter = book.Chapters[chapter_number - 1];
if (chapter != null)
{
Verse verse = chapter.Verses[verse_number - 1];
if (verse != null)
{
// add bismAllah manually to each chapter except 1 and 9
if (
((chapter_number != 1) && (chapter_number != 9))
&&
((verse_number == 1) && (word_number == 1) && (word_part_number == 1))
)
{
Verse bismAllah_verse = book.Verses[0];
// if there is no bismAllah, add one
if (parts[1] != bismAllah_verse.Words[0].Parts[0].Buckwalter)
{
// insert 4 new words
verse.Words.InsertRange(0, new List<Word>(4));
//(1:1:1:1) bi PP PREFIX|bi+
WordPart word_part = new WordPart(verse.Words[0],
bismAllah_verse.Words[0].Parts[0].NumberInWord,
bismAllah_verse.Words[0].Parts[0].Buckwalter,
bismAllah_verse.Words[0].Parts[0].Tag,
new WordPartGrammar(bismAllah_verse.Words[0].Parts[0].Grammar)
);
if ((chapter_number == 95) || (chapter_number == 97))
{
// add shadda { '~', 'ّ' } on B or bism
word_part.Buckwalter = word_part.Buckwalter.Insert(1, "~");
}
//(1:1:1:2) somi N STEM|POS:N|LEM:{som|ROOT:smw|M|GEN
new WordPart(verse.Words[0],
bismAllah_verse.Words[0].Parts[1].NumberInWord,
bismAllah_verse.Words[0].Parts[1].Buckwalter,
bismAllah_verse.Words[0].Parts[1].Tag,
new WordPartGrammar(bismAllah_verse.Words[0].Parts[1].Grammar)
);
//(1:1:2:1) {ll~ahi PN STEM|POS:PN|LEM:{ll~ah|ROOT:Alh|GEN
new WordPart(verse.Words[1],
bismAllah_verse.Words[1].Parts[0].NumberInWord,
bismAllah_verse.Words[1].Parts[0].Buckwalter,
bismAllah_verse.Words[1].Parts[0].Tag,
new WordPartGrammar(bismAllah_verse.Words[1].Parts[0].Grammar)
);
//(1:1:3:1) {l DET PREFIX|Al+
new WordPart(verse.Words[2],
bismAllah_verse.Words[2].Parts[0].NumberInWord,
bismAllah_verse.Words[2].Parts[0].Buckwalter,
bismAllah_verse.Words[2].Parts[0].Tag,
new WordPartGrammar(bismAllah_verse.Words[2].Parts[0].Grammar)
);
//(1:1:3:2) r~aHoma`ni ADJ STEM|POS:ADJ|LEM:r~aHoma`n|ROOT:rHm|MS|GEN
new WordPart(verse.Words[2],
bismAllah_verse.Words[2].Parts[1].NumberInWord,
bismAllah_verse.Words[2].Parts[1].Buckwalter,
bismAllah_verse.Words[2].Parts[1].Tag,
new WordPartGrammar(bismAllah_verse.Words[2].Parts[1].Grammar)
);
//(1:1:4:1) {l DET PREFIX|Al+
new WordPart(verse.Words[3],
bismAllah_verse.Words[3].Parts[0].NumberInWord,
bismAllah_verse.Words[3].Parts[0].Buckwalter,
bismAllah_verse.Words[3].Parts[0].Tag,
new WordPartGrammar(bismAllah_verse.Words[3].Parts[0].Grammar)
);
//(1:1:4:2) r~aHiymi ADJ STEM|POS:ADJ|LEM:r~aHiym|ROOT:rHm|MS|GEN
new WordPart(verse.Words[3],
bismAllah_verse.Words[3].Parts[1].NumberInWord,
bismAllah_verse.Words[3].Parts[1].Buckwalter,
bismAllah_verse.Words[3].Parts[1].Tag,
new WordPartGrammar(bismAllah_verse.Words[3].Parts[1].Grammar)
);
}
}
// correct word_number (if needed) for all subsequenct chapter word_parts
if (
((chapter_number != 1) && (chapter_number != 9)) && (verse_number == 1)
)
{
word_number += 4;
}
Word word = verse.Words[word_number - 1];
if (word != null)
{
List<string> grammar = new List<string>(parts[3].Split('|'));
if (grammar.Count > 0)
{
//(1:5:3:1) wa CONJ PREFIX|w_CONJ+
//(1:5:3:2) <iy~aAka PRON STEM|POS:PRON|LEM:<iy~aA|2MS
if (word.Text == "و")
{
waw_count++;
}
new WordPart(word, word_part_number, buckwalter, tag, grammar);
}
else
{
throw new Exception("Grammar field is missing.\r\n" + filename);
}
}
}
}
}
else
{
throw new Exception("Invalid Location Format.\r\n" + filename);
}
}
else
{
throw new Exception("Invalid File Format.\r\n" + filename);
}
}
}
catch (Exception ex)
{
throw new Exception("LoadWordParts: " + ex.Message);
}
}
}
}
}
}
// instance constructor
//Type Position Attribute Qualifier PersonDegree PersonGender PersonNumber Mood Lemma Root SpecialGroup
public WordPartGrammar(WordPart word_part, List <string> grammar)
{
if (word_part != null)
{
this.word_part = word_part;
if (grammar != null)
{
if (grammar.Count > 1)
{
this.type = grammar[0];
switch (this.type)
{
case "PREFIX":
{
//Al+
//bi+
//bip+
//ka+
//ta+
//sa+
//ya+
//ha+
//A_INTG+
//A_EQ+"
//b_PART+
//f_REM+
//f_CONJ+
//f_RSLT+
//f_SUP+
//f_CAUS+
//l_PP+
//l_EMPH+
//l_PRP+
//l_IMPV+
//w_CONJ+
//w_REM+
//w_CIRC+
//w_SUP+
//w_PP+
//w_COM+
if (grammar.Count == 2)
{
this.position = grammar[1];
}
else
{
throw new Exception("WordPartGrammar: Invalide PREFIX at word part " + word_part.Address);
}
}
break;
case "STEM":
{
for (int i = 1; i < grammar.Count; i++)
{
string[] parts = grammar[i].Split(':');
if (parts.Length == 2)
{
if (parts[0] == "POS")
{
//INL
//N
//PN
//V
//ADJ
//IMPN
//AC
//AMD
//ANS
//AVR
//CERT
//COND
//EXH
//EXL
//EXP
//FUT
//INC
//INT
//INTG
//NEG
//PREV
//PRO
//RES
//RET
//SUP
//SUR
//PP
//CONJ
//SUB
//EQ
//REM
//CIRC
//COM
//RSLT
//CAUS
//EMPH
//PRP
//IMPV
//PRON
//DEM
//REL
//T
//LOC
this.position = parts[1];
}
else if (parts[0] == "LEM")
{
this.lemma = parts[1];
}
else if (parts[0] == "ROOT")
{
this.root = parts[1];
}
else if (parts[0] == "SP")
{
this.special_group = parts[1];
}
else if (parts[0] == "MOOD")
{
this.mood = parts[1];
}
else
{
throw new Exception("WordPartGrammar: Invalide STEM at word part " + word_part.Address);
}
}
else if (parts.Length == 1) // attribute or qualifier
{
switch (parts[0])
{
case "1":
case "2":
case "3":
this.person_degree = parts[0][0].ToString();
break;
case "M":
case "F":
this.person_gender = parts[0][0].ToString();
break;
case "S":
case "D":
case "P":
this.person_number = parts[0][0].ToString();
break;
case "1M":
case "2M":
case "3M":
case "1F":
case "2F":
case "3F":
this.person_degree = parts[0][0].ToString();
this.person_gender = parts[0][1].ToString();
break;
case "1S":
case "2S":
case "3S":
case "1D":
case "2D":
case "3D":
case "1P":
case "2P":
case "3P":
this.person_degree = parts[0][0].ToString();
this.person_number = parts[0][1].ToString();
break;
case "MS":
case "FS":
case "MD":
case "FD":
case "MP":
case "FP":
this.person_gender = parts[0][0].ToString();
this.person_number = parts[0][1].ToString();
break;
case "1MS":
case "2MS":
case "3MS":
case "1FS":
case "2FS":
case "3FS":
case "1MD":
case "2MD":
case "3MD":
case "1FD":
case "2FD":
case "3FD":
case "1MP":
case "2MP":
case "3MP":
case "1FP":
case "2FP":
case "3FP":
this.person_degree = parts[0][0].ToString();
this.person_gender = parts[0][1].ToString();
this.person_number = parts[0][2].ToString();
break;
default:
if (String.IsNullOrEmpty(this.attribute))
{
//VN
//ACT_PCPL
//PASS_PCPL
//NOM
//ACC
//GEN
//DEF
//INDEF
//PERF
//IMPF
//IMPV
this.attribute = parts[0];
}
else
{
//NOM
//ACC
//ACT
//PASS
//(I)
//(II)
//(III)
//(IV)
//(V)
//(VI)
//(VII)
//(VIII)
//(IX)
//(X)
//(XI)
//(XII)
this.qualifier = parts[0];
}
break;
}
}
}
}
break;
case "SUFFIX":
{
if (grammar.Count == 2)
{
//SUFFIX|+n_EMPH
//SUFFIX|+VOC
//SUFFIX|+l_PP
//SUFFIX|+PRON:2MP
//SUFFIX|+A_SILENT
string[] parts = grammar[1].Split(':');
if (parts.Length == 1)
{
this.position = parts[0];
}
else if (parts.Length == 2)
{
if (parts[0] == "+PRON")
{
this.position = parts[0];
if (parts[1].Length == 3)
{
this.person_degree = parts[1][0].ToString();
this.person_gender = parts[1][1].ToString();
this.person_number = parts[1][2].ToString();
}
else if (parts[1].Length == 2)
{
if ((parts[1][0] == '1') || (parts[1][0] == '2') || (parts[1][0] == '3'))
{
this.person_degree = parts[1][0].ToString();
}
else if ((parts[1][0] == 'M') || (parts[1][0] == 'F'))
{
this.person_gender = parts[1][0].ToString();
}
else if ((parts[1][0] == 'S') || (parts[1][0] == 'D') || (parts[1][0] == 'P'))
{
this.person_number = parts[1][0].ToString();
}
if ((parts[1][1] == 'M') || (parts[1][1] == 'F'))
{
this.person_gender = parts[1][1].ToString();
}
else if ((parts[1][1] == 'S') || (parts[1][1] == 'D') || (parts[1][1] == 'P'))
{
this.person_number = parts[1][1].ToString();
}
}
else if (parts[1].Length == 1)
{
if ((parts[1][0] == '1') || (parts[1][0] == '2') || (parts[1][0] == '3'))
{
this.person_degree = parts[1][0].ToString();
}
else if ((parts[1][0] == 'M') || (parts[1][0] == 'F'))
{
this.person_gender = parts[1][0].ToString();
}
else if ((parts[1][0] == 'S') || (parts[1][0] == 'D') || (parts[1][0] == 'P'))
{
this.person_number = parts[1][0].ToString();
}
}
}
else
{
throw new Exception("WordPartGrammar: SUFFIX|+PRON expected at word part " + word_part.Address);
}
}
else
{
throw new Exception("WordPartGrammar: Invalide SUFFIX at word part " + word_part.Address);
}
}
else
{
throw new Exception("WordPartGrammar: Invalide SUFFIX at word part " + word_part.Address);
}
}
break;
default:
break;
}
}
}
}
}
