first upload

.gitignore

@@ -0,0 +1 @@
+env/

const.py

@@ -0,0 +1,1455 @@
+LATEX_VOC = ['\\overrightarrow{\\rm AB}',
+ '\\overleftrightarrow',
+ '\\Longleftrightarrow',
+ '\\longleftrightarrow',
+ '\\supsetneqq\\gtrsim',
+ '\\scriptscriptstyle',
+ '\\rightleftharpoons',
+ '\\circlearrowright',
+ '\\overline{\\rm AB}',
+ '\\rightrightarrows',
+ '\\leftrightarrows',
+ '\\rightleftarrows',
+ '\\curvearrowright',
+ '\\circlearrowleft',
+ '\\bigtriangledown',
+ '\\leftleftarrows',
+ '\\longrightarrow',
+ '\\Leftrightarrow',
+ '\\Longrightarrow',
+ '\\curvearrowleft',
+ '\\hookrightarrow',
+ '\\rightharpoonup',
+ '\\leftrightarrow',
+ '\\overrightarrow',
+ '\\longleftarrow',
+ '\\bigtriangleup',
+ '\\overleftarrow',
+ '\\triangleright',
+ '\\operatorname*',
+ '\\hookleftarrow',
+ '\\varsubsetneqq',
+ '\\Longleftarrow',
+ '\\arraystretch',
+ '\\right\\rfloor',
+ '\\right\\rbrace',
+ '\\footnotesize',
+ '\\begin{array}',
+ '\\right\\rangle',
+ '\\displaystyle',
+ '\\operatorname',
+ '\\renewcommand',
+ '\\right\\rbrack',
+ '\\triangleleft',
+ '\\arraycolsep',
+ '\\updownarrow',
+ '\\diamondsuit',
+ '\\left\\lbrace',
+ '\\nolinebreak',
+ '\\scriptstyle',
+ '\\left\\lfloor',
+ '\\left\\langle',
+ '\\left\\lbrack',
+ '\\multicolumn',
+ '\\mathversion',
+ '\\not\\supset',
+ '\\complement',
+ '\\unitlength',
+ '\\thicklines',
+ '\\rightarrow',
+ '\\varnothing',
+ '\\right\\vert',
+ '\\sqsupseteq',
+ '\\supsetneqq',
+ '\\not\\subset',
+ '\\scriptsize',
+ '\\Rightarrow',
+ '\\boldsymbol',
+ '\\ensuremath',
+ '\\curlywedge',
+ '\\textnormal',
+ '\\normalsize',
+ '\\end{array}',
+ '\\sqsubseteq',
+ '\\varepsilon',
+ '\\setcounter',
+ '\\unboldmath',
+ '\\underbrace',
+ '\\circledast',
+ '\\longmapsto',
+ '\\nsubseteq',
+ '\\backslash',
+ '\\thinspace',
+ '\\smallskip',
+ '\\leftarrow',
+ '\\llbracket',
+ '\\Leftarrow',
+ '\\setlength',
+ '\\triangleq',
+ '\\arrowvert',
+ '\\subsetneq',
+ '\\supseteqq',
+ '\\mathbb{H}',
+ '\\varlimsup',
+ '\\left\\vert',
+ '\\downarrow',
+ '\\mathbb{S}',
+ '\\nparallel',
+ '\\widetilde',
+ '\\Downarrow',
+ '\\nsupseteq',
+ '\\overbrace',
+ '\\textstyle',
+ '\\varliminf',
+ '\\checkmark',
+ '\\supsetneq',
+ '\\bigotimes',
+ '\\pitchfork',
+ '\\mathbb{A}',
+ '\\underline',
+ '\\mathbb{O}',
+ '\\righarrow',
+ '\\hphantom',
+ '\\parallel',
+ '\\leqslant',
+ '\\underset',
+ '\\subseteq',
+ '\\bigsqcup',
+ '\\bigoplus',
+ '\\multiput',
+ '\\ulcorner',
+ '\\raisebox',
+ '\\bigwedge',
+ '\\emptyset',
+ '\\protectu',
+ '\\boxminus',
+ '\\buildrel',
+ '\\vartheta',
+ '\\overline',
+ '\\framebox',
+ '\\mathfrak',
+ '\\smallint',
+ '\\stackrel',
+ '\\sqsupset',
+ '\\llcorner',
+ '\\sqsubset',
+ '\\lrcorner',
+ '\\curlyvee',
+ '\\nonumber',
+ '\\substack',
+ '\\supseteq',
+ '\\varsigma',
+ '\\biguplus',
+ '\\triangle',
+ '\\setminus',
+ '\\vphantom',
+ '\\boldmath',
+ '\\geqslant',
+ '\\upsilon',
+ '\\diamond',
+ '\\epsilon',
+ '\\noalign',
+ '\\medskip',
+ '\\lessdot',
+ '\\bigcirc',
+ '\\protect',
+ '\\right\\|',
+ '\\boxplus',
+ '\\special',
+ '\\nearrow',
+ '\\right\\}',
+ '\\because',
+ '\\widehat',
+ '\\phantom',
+ '\\itshape',
+ '\\lessgtr',
+ '\\mathbin',
+ '\\lefteqn',
+ '\\backsim',
+ '\\makebox',
+ '\\mathscr',
+ '\\searrow',
+ '\\ooalign',
+ '\\Upsilon',
+ '\\natural',
+ '\\enspace',
+ '\\partial',
+ '\\uparrow',
+ '\\newline',
+ '\\ddagger',
+ '\\cooking',
+ '\\lesssim',
+ '\\nexists',
+ '\\bigodot',
+ '\\nwarrow',
+ '\\mathcal',
+ '\\mathrel',
+ '\\gtrless',
+ '\\vcenter',
+ '\\swarrow',
+ '\\fboxsep',
+ '\\omicron',
+ '\\leadsto',
+ '\\Subset',
+ '\\mathit',
+ '\\lambda',
+ '\\varphi',
+ '\\rbrace',
+ '\\textit',
+ '\\supset',
+ '\\textup',
+ '\\otimes',
+ '\\mathbf',
+ '\\right|',
+ '\\lbrace',
+ '\\forall',
+ '\\square',
+ '\\varrho',
+ '\\arctan',
+ '\\rtimes',
+ '\\right>',
+ '\\textrm',
+ '\\texttt',
+ '\\textsf',
+ '\\models',
+ '\\bigvee',
+ '\\langle',
+ '\\dagger',
+ '\\arccot',
+ '\\mapsto',
+ '\\succeq',
+ '\\lbrack',
+ '\\bullet',
+ '\\textbf',
+ '\\gtrsim',
+ '\\bigcap',
+ '\\nvdash',
+ '\\Lambda',
+ '\\arccos',
+ '\\lceilm',
+ '\\rgroup',
+ '\\coprod',
+ '\\ominus',
+ '\\approx',
+ '\\parbox',
+ '\\lfloor',
+ '\\bigcup',
+ '\\left\\{',
+ '\\oslash',
+ '\\enskip',
+ '\\ltimes',
+ '\\rangle',
+ '\\rfloor',
+ '\\propto',
+ '\\mathsf',
+ '\\lgroup',
+ '\\pounds',
+ '\\rbrack',
+ '\\mathrm',
+ '\\subset',
+ '\\left\\|',
+ '\\mathop',
+ '\\circle',
+ '\\right.',
+ '\\mathbb',
+ '\\exists',
+ '\\arcsin',
+ '\\prime',
+ '\\vline',
+ '\\cdots',
+ '\\varpi',
+ '\\notin',
+ '\\Theta',
+ '\\sqcup',
+ '\\left<',
+ '\\Gamma',
+ '\\theta',
+ '\\label',
+ '\\right',
+ '\\simeq',
+ '\\infty',
+ '\\mskip',
+ '\\Large',
+ '\\asymp',
+ '\\sharp',
+ '\\left.',
+ '\\dashv',
+ '\\lceil',
+ '\\omega',
+ '\\dddot',
+ '\\ldots',
+ '\\qquad',
+ '\\alpha',
+ '\\Biggm',
+ '\\check',
+ '\\smile',
+ '\\vDash',
+ '\\grave',
+ '\\nless',
+ '\\sqcap',
+ '\\delta',
+ '\\doteq',
+ '\\Omega',
+ '\\Biggl',
+ '\\mkern',
+ '\\Biggr',
+ '\\hline',
+ '\\LARGE',
+ '\\smash',
+ '\\small',
+ '\\aleph',
+ '\\equiv',
+ '\\tilde',
+ '\\space',
+ '\\rceil',
+ '\\raise',
+ '\\unlhd',
+ '\\binom',
+ '\\gamma',
+ '\\vskip',
+ '\\strut',
+ '\\biggl',
+ '\\colon',
+ '\\cdotp',
+ '\\amalg',
+ '\\kappa',
+ '\\hrule',
+ '\\jmath',
+ '\\lower',
+ '\\breve',
+ '\\sigma',
+ '\\vdash',
+ '\\wedge',
+ '\\large',
+ '\\nabla',
+ '\\hfill',
+ '\\Sigma',
+ '\\biggr',
+ '\\relax',
+ '\\Delta',
+ '\\begin',
+ '\\unrhd',
+ '\\acute',
+ '\\vdots',
+ '\\left|',
+ '\\oplus',
+ '\\slash',
+ '\\ddots',
+ '\\times',
+ '\\imath',
+ '\\angle',
+ '\\vrule',
+ '\\Huge',
+ '\\bmod',
+ '\\geqq',
+ '\\null',
+ '\\kern',
+ '\\nsim',
+ '\\nleq',
+ '\\Bigl',
+ '\\Perp',
+ '\\each',
+ '\\land',
+ '\\bigr',
+ '\\Vert',
+ '\\tanh',
+ '\\hfil',
+ '\\circ',
+ '\\prec',
+ '\\iota',
+ '\\odot',
+ '\\line',
+ '\\sent',
+ '\\prod',
+ '\\atop',
+ '\\iint',
+ '\\Reef',
+ '\\ngeq',
+ '\\cite',
+ '\\tiny',
+ '\\ddot',
+ '\\nmid',
+ '\\rlap',
+ '\\bigg',
+ '\\Bigm',
+ '\\flat',
+ '\\midf',
+ '\\cosh',
+ '\\llap',
+ '\\surd',
+ '\\perp',
+ '\\star',
+ '\\fbox',
+ '\\dots',
+ '\\vert',
+ '\\bigm',
+ '\\ddag',
+ '\\taxi',
+ '\\oint',
+ '\\frac',
+ '\\left',
+ '\\text',
+ '\\crcr',
+ '\\cong',
+ '\\zeta',
+ '\\ngtr',
+ '\\Bigg',
+ '\\pmod',
+ '\\skew',
+ '\\quad',
+ '\\Bigr',
+ '\\beta',
+ '\\leqq',
+ '\\hbar',
+ '\\bigl',
+ '\\sinh',
+ '\\sqrt',
+ '\\cdot',
+ '\\not',
+ '\\div',
+ '\\put',
+ '\\lll',
+ '\\tau',
+ '\\sum',
+ '\\lor',
+ '\\eta',
+ '\\min',
+ '\\rho',
+ '\\mid',
+ '\\neg',
+ '\\cao',
+ '\\end',
+ '\\vee',
+ '\\int',
+ '\\ref',
+ '\\geq',
+ '\\cap',
+ '\\hat',
+ '\\phi',
+ '\\mit',
+ '\\sin',
+ '\\cot',
+ '\\ggg',
+ '\\cos',
+ '\\mho',
+ '\\hss',
+ '\\Big',
+ '\\top',
+ '\\for',
+ '\\lim',
+ '\\eth',
+ '\\cal',
+ '\\dag',
+ '\\log',
+ '\\vss',
+ '\\arg',
+ '\\Phi',
+ '\\psi',
+ '\\dot',
+ '\\bar',
+ '\\leq',
+ '\\bot',
+ '\\ell',
+ '\\sec',
+ '\\tan',
+ '\\sim',
+ '\\Psi',
+ '\\dog',
+ '\\chi',
+ '\\big',
+ '\\cup',
+ '\\his',
+ '\\odd',
+ '\\ast',
+ '\\neq',
+ '\\max',
+ '\\vec',
+ '\\sup',
+ '\\le',
+ '\\bf',
+ '\\Em',
+ '\\lq',
+ '\\lg',
+ '\\sc',
+ '\\nu',
+ '\\ln',
+ '\\mp',
+ '\\Im',
+ '\\Pi',
+ '\\do',
+ '\\it',
+ '\\gt',
+ '\\wp',
+ '\\ll',
+ '\\ge',
+ '\\AA',
+ '\\tt',
+ '\\sp',
+ '\\ae',
+ '\\Xi',
+ '\\sf',
+ '\\mu',
+ '\\sb',
+ '\\ni',
+ '\\Re',
+ '\\rm',
+ '\\ss',
+ '\\pm',
+ '\\em',
+ '\\to',
+ '\\ne',
+ '\\in',
+ '\\tg',
+ '\\gg',
+ '\\xi',
+ '\\sl',
+ '\\pi',
+ '\\SS',
+ '\\%',
+ '\\S',
+ '\\A',
+ '\\P',
+ '\\_',
+ '\\:',
+ '\\;',
+ '\\*',
+ '\\$',
+ '\\>',
+ '\\x',
+ '\\/',
+ '\\+',
+ '\\}',
+ '\\B',
+ '\\&',
+ '\\R',
+ '\\l',
+ '\\L',
+ '\\|',
+ '\\,',
+ '\\{',
+ '\\n',
+ '\\m',
+ '\\=',
+ '\\z',
+ "\\'",
+ '\\!',
+ '\\<',
+ '\\Z',
+ '\\o',
+ '\\O',
+ '\\T',
+ '\\a',
+ '\\C',
+ '\\^',
+ '\\y',
+ '\\\\',
+ '\\i',
+ '\\c',
+ '\\#',
+ '\\-',
+ '\\N',
+ '\\b',
+ '\\j',
+ '\\d',
+ '\\Q',
+ ']',
+ '^',
+ '_',
+ '\\']
+
+TOKEN_LATEX_VOC = ['\\ o v e r r i g h t a r r o w { \\ r m   A B }',
+ '\\ o v e r l e f t r i g h t a r r o w',
+ '\\ L o n g l e f t r i g h t a r r o w',
+ '\\ l o n g l e f t r i g h t a r r o w',
+ '\\ s u p s e t n e q q \\ g t r s i m',
+ '\\ s c r i p t s c r i p t s t y l e',
+ '\\ r i g h t l e f t h a r p o o n s',
+ '\\ c i r c l e a r r o w r i g h t',
+ '\\ o v e r l i n e { \\ r m   A B }',
+ '\\ r i g h t r i g h t a r r o w s',
+ '\\ l e f t r i g h t a r r o w s',
+ '\\ r i g h t l e f t a r r o w s',
+ '\\ c u r v e a r r o w r i g h t',
+ '\\ c i r c l e a r r o w l e f t',
+ '\\ b i g t r i a n g l e d o w n',
+ '\\ l e f t l e f t a r r o w s',
+ '\\ l o n g r i g h t a r r o w',
+ '\\ L e f t r i g h t a r r o w',
+ '\\ L o n g r i g h t a r r o w',
+ '\\ c u r v e a r r o w l e f t',
+ '\\ h o o k r i g h t a r r o w',
+ '\\ r i g h t h a r p o o n u p',
+ '\\ l e f t r i g h t a r r o w',
+ '\\ o v e r r i g h t a r r o w',
+ '\\ l o n g l e f t a r r o w',
+ '\\ b i g t r i a n g l e u p',
+ '\\ o v e r l e f t a r r o w',
+ '\\ t r i a n g l e r i g h t',
+ '\\ o p e r a t o r n a m e *',
+ '\\ h o o k l e f t a r r o w',
+ '\\ v a r s u b s e t n e q q',
+ '\\ L o n g l e f t a r r o w',
+ '\\ a r r a y s t r e t c h',
+ '\\ r i g h t \\ r f l o o r',
+ '\\ r i g h t \\ r b r a c e',
+ '\\ f o o t n o t e s i z e',
+ '\\ b e g i n { a r r a y }',
+ '\\ r i g h t \\ r a n g l e',
+ '\\ d i s p l a y s t y l e',
+ '\\ o p e r a t o r n a m e',
+ '\\ r e n e w c o m m a n d',
+ '\\ r i g h t \\ r b r a c k',
+ '\\ t r i a n g l e l e f t',
+ '\\ a r r a y c o l s e p',
+ '\\ u p d o w n a r r o w',
+ '\\ d i a m o n d s u i t',
+ '\\ l e f t \\ l b r a c e',
+ '\\ n o l i n e b r e a k',
+ '\\ s c r i p t s t y l e',
+ '\\ l e f t \\ l f l o o r',
+ '\\ l e f t \\ l a n g l e',
+ '\\ l e f t \\ l b r a c k',
+ '\\ m u l t i c o l u m n',
+ '\\ m a t h v e r s i o n',
+ '\\ n o t \\ s u p s e t',
+ '\\ c o m p l e m e n t',
+ '\\ u n i t l e n g t h',
+ '\\ t h i c k l i n e s',
+ '\\ r i g h t a r r o w',
+ '\\ v a r n o t h i n g',
+ '\\ r i g h t \\ v e r t',
+ '\\ s q s u p s e t e q',
+ '\\ s u p s e t n e q q',
+ '\\ n o t \\ s u b s e t',
+ '\\ s c r i p t s i z e',
+ '\\ R i g h t a r r o w',
+ '\\ b o l d s y m b o l',
+ '\\ e n s u r e m a t h',
+ '\\ c u r l y w e d g e',
+ '\\ t e x t n o r m a l',
+ '\\ n o r m a l s i z e',
+ '\\ e n d { a r r a y }',
+ '\\ s q s u b s e t e q',
+ '\\ v a r e p s i l o n',
+ '\\ s e t c o u n t e r',
+ '\\ u n b o l d m a t h',
+ '\\ u n d e r b r a c e',
+ '\\ c i r c l e d a s t',
+ '\\ l o n g m a p s t o',
+ '\\ n s u b s e t e q',
+ '\\ b a c k s l a s h',
+ '\\ t h i n s p a c e',
+ '\\ s m a l l s k i p',
+ '\\ l e f t a r r o w',
+ '\\ l l b r a c k e t',
+ '\\ L e f t a r r o w',
+ '\\ s e t l e n g t h',
+ '\\ t r i a n g l e q',
+ '\\ a r r o w v e r t',
+ '\\ s u b s e t n e q',
+ '\\ s u p s e t e q q',
+ '\\ m a t h b b { H }',
+ '\\ v a r l i m s u p',
+ '\\ l e f t \\ v e r t',
+ '\\ d o w n a r r o w',
+ '\\ m a t h b b { S }',
+ '\\ n p a r a l l e l',
+ '\\ w i d e t i l d e',
+ '\\ D o w n a r r o w',
+ '\\ n s u p s e t e q',
+ '\\ o v e r b r a c e',
+ '\\ t e x t s t y l e',
+ '\\ v a r l i m i n f',
+ '\\ c h e c k m a r k',
+ '\\ s u p s e t n e q',
+ '\\ b i g o t i m e s',
+ '\\ p i t c h f o r k',
+ '\\ m a t h b b { A }',
+ '\\ u n d e r l i n e',
+ '\\ m a t h b b { O }',
+ '\\ r i g h a r r o w',
+ '\\ h p h a n t o m',
+ '\\ p a r a l l e l',
+ '\\ l e q s l a n t',
+ '\\ u n d e r s e t',
+ '\\ s u b s e t e q',
+ '\\ b i g s q c u p',
+ '\\ b i g o p l u s',
+ '\\ m u l t i p u t',
+ '\\ u l c o r n e r',
+ '\\ r a i s e b o x',
+ '\\ b i g w e d g e',
+ '\\ e m p t y s e t',
+ '\\ p r o t e c t u',
+ '\\ b o x m i n u s',
+ '\\ b u i l d r e l',
+ '\\ v a r t h e t a',
+ '\\ o v e r l i n e',
+ '\\ f r a m e b o x',
+ '\\ m a t h f r a k',
+ '\\ s m a l l i n t',
+ '\\ s t a c k r e l',
+ '\\ s q s u p s e t',
+ '\\ l l c o r n e r',
+ '\\ s q s u b s e t',
+ '\\ l r c o r n e r',
+ '\\ c u r l y v e e',
+ '\\ n o n u m b e r',
+ '\\ s u b s t a c k',
+ '\\ s u p s e t e q',
+ '\\ v a r s i g m a',
+ '\\ b i g u p l u s',
+ '\\ t r i a n g l e',
+ '\\ s e t m i n u s',
+ '\\ v p h a n t o m',
+ '\\ b o l d m a t h',
+ '\\ g e q s l a n t',
+ '\\ u p s i l o n',
+ '\\ d i a m o n d',
+ '\\ e p s i l o n',
+ '\\ n o a l i g n',
+ '\\ m e d s k i p',
+ '\\ l e s s d o t',
+ '\\ b i g c i r c',
+ '\\ p r o t e c t',
+ '\\ r i g h t \\ |',
+ '\\ b o x p l u s',
+ '\\ s p e c i a l',
+ '\\ n e a r r o w',
+ '\\ r i g h t \\ }',
+ '\\ b e c a u s e',
+ '\\ w i d e h a t',
+ '\\ p h a n t o m',
+ '\\ i t s h a p e',
+ '\\ l e s s g t r',
+ '\\ m a t h b i n',
+ '\\ l e f t e q n',
+ '\\ b a c k s i m',
+ '\\ m a k e b o x',
+ '\\ m a t h s c r',
+ '\\ s e a r r o w',
+ '\\ o o a l i g n',
+ '\\ U p s i l o n',
+ '\\ n a t u r a l',
+ '\\ e n s p a c e',
+ '\\ p a r t i a l',
+ '\\ u p a r r o w',
+ '\\ n e w l i n e',
+ '\\ d d a g g e r',
+ '\\ c o o k i n g',
+ '\\ l e s s s i m',
+ '\\ n e x i s t s',
+ '\\ b i g o d o t',
+ '\\ n w a r r o w',
+ '\\ m a t h c a l',
+ '\\ m a t h r e l',
+ '\\ g t r l e s s',
+ '\\ v c e n t e r',
+ '\\ s w a r r o w',
+ '\\ f b o x s e p',
+ '\\ o m i c r o n',
+ '\\ l e a d s t o',
+ '\\ S u b s e t',
+ '\\ m a t h i t',
+ '\\ l a m b d a',
+ '\\ v a r p h i',
+ '\\ r b r a c e',
+ '\\ t e x t i t',
+ '\\ s u p s e t',
+ '\\ t e x t u p',
+ '\\ o t i m e s',
+ '\\ m a t h b f',
+ '\\ r i g h t |',
+ '\\ l b r a c e',
+ '\\ f o r a l l',
+ '\\ s q u a r e',
+ '\\ v a r r h o',
+ '\\ a r c t a n',
+ '\\ r t i m e s',
+ '\\ r i g h t >',
+ '\\ t e x t r m',
+ '\\ t e x t t t',
+ '\\ t e x t s f',
+ '\\ m o d e l s',
+ '\\ b i g v e e',
+ '\\ l a n g l e',
+ '\\ d a g g e r',
+ '\\ a r c c o t',
+ '\\ m a p s t o',
+ '\\ s u c c e q',
+ '\\ l b r a c k',
+ '\\ b u l l e t',
+ '\\ t e x t b f',
+ '\\ g t r s i m',
+ '\\ b i g c a p',
+ '\\ n v d a s h',
+ '\\ L a m b d a',
+ '\\ a r c c o s',
+ '\\ l c e i l m',
+ '\\ r g r o u p',
+ '\\ c o p r o d',
+ '\\ o m i n u s',
+ '\\ a p p r o x',
+ '\\ p a r b o x',
+ '\\ l f l o o r',
+ '\\ b i g c u p',
+ '\\ l e f t \\ {',
+ '\\ o s l a s h',
+ '\\ e n s k i p',
+ '\\ l t i m e s',
+ '\\ r a n g l e',
+ '\\ r f l o o r',
+ '\\ p r o p t o',
+ '\\ m a t h s f',
+ '\\ l g r o u p',
+ '\\ p o u n d s',
+ '\\ r b r a c k',
+ '\\ m a t h r m',
+ '\\ s u b s e t',
+ '\\ l e f t \\ |',
+ '\\ m a t h o p',
+ '\\ c i r c l e',
+ '\\ r i g h t .',
+ '\\ m a t h b b',
+ '\\ e x i s t s',
+ '\\ a r c s i n',
+ '\\ p r i m e',
+ '\\ v l i n e',
+ '\\ c d o t s',
+ '\\ v a r p i',
+ '\\ n o t i n',
+ '\\ T h e t a',
+ '\\ s q c u p',
+ '\\ l e f t <',
+ '\\ G a m m a',
+ '\\ t h e t a',
+ '\\ l a b e l',
+ '\\ r i g h t',
+ '\\ s i m e q',
+ '\\ i n f t y',
+ '\\ m s k i p',
+ '\\ L a r g e',
+ '\\ a s y m p',
+ '\\ s h a r p',
+ '\\ l e f t .',
+ '\\ d a s h v',
+ '\\ l c e i l',
+ '\\ o m e g a',
+ '\\ d d d o t',
+ '\\ l d o t s',
+ '\\ q q u a d',
+ '\\ a l p h a',
+ '\\ B i g g m',
+ '\\ c h e c k',
+ '\\ s m i l e',
+ '\\ v D a s h',
+ '\\ g r a v e',
+ '\\ n l e s s',
+ '\\ s q c a p',
+ '\\ d e l t a',
+ '\\ d o t e q',
+ '\\ O m e g a',
+ '\\ B i g g l',
+ '\\ m k e r n',
+ '\\ B i g g r',
+ '\\ h l i n e',
+ '\\ L A R G E',
+ '\\ s m a s h',
+ '\\ s m a l l',
+ '\\ a l e p h',
+ '\\ e q u i v',
+ '\\ t i l d e',
+ '\\ s p a c e',
+ '\\ r c e i l',
+ '\\ r a i s e',
+ '\\ u n l h d',
+ '\\ b i n o m',
+ '\\ g a m m a',
+ '\\ v s k i p',
+ '\\ s t r u t',
+ '\\ b i g g l',
+ '\\ c o l o n',
+ '\\ c d o t p',
+ '\\ a m a l g',
+ '\\ k a p p a',
+ '\\ h r u l e',
+ '\\ j m a t h',
+ '\\ l o w e r',
+ '\\ b r e v e',
+ '\\ s i g m a',
+ '\\ v d a s h',
+ '\\ w e d g e',
+ '\\ l a r g e',
+ '\\ n a b l a',
+ '\\ h f i l l',
+ '\\ S i g m a',
+ '\\ b i g g r',
+ '\\ r e l a x',
+ '\\ D e l t a',
+ '\\ b e g i n',
+ '\\ u n r h d',
+ '\\ a c u t e',
+ '\\ v d o t s',
+ '\\ l e f t |',
+ '\\ o p l u s',
+ '\\ s l a s h',
+ '\\ d d o t s',
+ '\\ t i m e s',
+ '\\ i m a t h',
+ '\\ a n g l e',
+ '\\ v r u l e',
+ '\\ H u g e',
+ '\\ b m o d',
+ '\\ g e q q',
+ '\\ n u l l',
+ '\\ k e r n',
+ '\\ n s i m',
+ '\\ n l e q',
+ '\\ B i g l',
+ '\\ P e r p',
+ '\\ e a c h',
+ '\\ l a n d',
+ '\\ b i g r',
+ '\\ V e r t',
+ '\\ t a n h',
+ '\\ h f i l',
+ '\\ c i r c',
+ '\\ p r e c',
+ '\\ i o t a',
+ '\\ o d o t',
+ '\\ l i n e',
+ '\\ s e n t',
+ '\\ p r o d',
+ '\\ a t o p',
+ '\\ i i n t',
+ '\\ R e e f',
+ '\\ n g e q',
+ '\\ c i t e',
+ '\\ t i n y',
+ '\\ d d o t',
+ '\\ n m i d',
+ '\\ r l a p',
+ '\\ b i g g',
+ '\\ B i g m',
+ '\\ f l a t',
+ '\\ m i d f',
+ '\\ c o s h',
+ '\\ l l a p',
+ '\\ s u r d',
+ '\\ p e r p',
+ '\\ s t a r',
+ '\\ f b o x',
+ '\\ d o t s',
+ '\\ v e r t',
+ '\\ b i g m',
+ '\\ d d a g',
+ '\\ t a x i',
+ '\\ o i n t',
+ '\\ f r a c',
+ '\\ l e f t',
+ '\\ t e x t',
+ '\\ c r c r',
+ '\\ c o n g',
+ '\\ z e t a',
+ '\\ n g t r',
+ '\\ B i g g',
+ '\\ p m o d',
+ '\\ s k e w',
+ '\\ q u a d',
+ '\\ B i g r',
+ '\\ b e t a',
+ '\\ l e q q',
+ '\\ h b a r',
+ '\\ b i g l',
+ '\\ s i n h',
+ '\\ s q r t',
+ '\\ c d o t',
+ '\\ n o t',
+ '\\ d i v',
+ '\\ p u t',
+ '\\ l l l',
+ '\\ t a u',
+ '\\ s u m',
+ '\\ l o r',
+ '\\ e t a',
+ '\\ m i n',
+ '\\ r h o',
+ '\\ m i d',
+ '\\ n e g',
+ '\\ c a o',
+ '\\ e n d',
+ '\\ v e e',
+ '\\ i n t',
+ '\\ r e f',
+ '\\ g e q',
+ '\\ c a p',
+ '\\ h a t',
+ '\\ p h i',
+ '\\ m i t',
+ '\\ s i n',
+ '\\ c o t',
+ '\\ g g g',
+ '\\ c o s',
+ '\\ m h o',
+ '\\ h s s',
+ '\\ B i g',
+ '\\ t o p',
+ '\\ f o r',
+ '\\ l i m',
+ '\\ e t h',
+ '\\ c a l',
+ '\\ d a g',
+ '\\ l o g',
+ '\\ v s s',
+ '\\ a r g',
+ '\\ P h i',
+ '\\ p s i',
+ '\\ d o t',
+ '\\ b a r',
+ '\\ l e q',
+ '\\ b o t',
+ '\\ e l l',
+ '\\ s e c',
+ '\\ t a n',
+ '\\ s i m',
+ '\\ P s i',
+ '\\ d o g',
+ '\\ c h i',
+ '\\ b i g',
+ '\\ c u p',
+ '\\ h i s',
+ '\\ o d d',
+ '\\ a s t',
+ '\\ n e q',
+ '\\ m a x',
+ '\\ v e c',
+ '\\ s u p',
+ '\\ l e',
+ '\\ b f',
+ '\\ E m',
+ '\\ l q',
+ '\\ l g',
+ '\\ s c',
+ '\\ n u',
+ '\\ l n',
+ '\\ m p',
+ '\\ I m',
+ '\\ P i',
+ '\\ d o',
+ '\\ i t',
+ '\\ g t',
+ '\\ w p',
+ '\\ l l',
+ '\\ g e',
+ '\\ A A',
+ '\\ t t',
+ '\\ s p',
+ '\\ a e',
+ '\\ X i',
+ '\\ s f',
+ '\\ m u',
+ '\\ s b',
+ '\\ n i',
+ '\\ R e',
+ '\\ r m',
+ '\\ s s',
+ '\\ p m',
+ '\\ e m',
+ '\\ t o',
+ '\\ n e',
+ '\\ i n',
+ '\\ t g',
+ '\\ g g',
+ '\\ x i',
+ '\\ s l',
+ '\\ p i',
+ '\\ S S',
+ '\\ %',
+ '\\ S',
+ '\\ A',
+ '\\ P',
+ '\\ _',
+ '\\ :',
+ '\\ ;',
+ '\\ *',
+ '\\ $',
+ '\\ >',
+ '\\ x',
+ '\\ /',
+ '\\ +',
+ '\\ }',
+ '\\ B',
+ '\\ &',
+ '\\ R',
+ '\\ l',
+ '\\ L',
+ '\\ |',
+ '\\ ,',
+ '\\ {',
+ '\\ n',
+ '\\ m',
+ '\\ =',
+ '\\ z',
+ "\\ '",
+ '\\ !',
+ '\\ <',
+ '\\ Z',
+ '\\ o',
+ '\\ O',
+ '\\ T',
+ '\\ a',
+ '\\ C',
+ '\\ ^',
+ '\\ y',
+ '\\ \\',
+ '\\ i',
+ '\\ c',
+ '\\ #',
+ '\\ -',
+ '\\ N',
+ '\\ b',
+ '\\ j',
+ '\\ d',
+ '\\ Q',
+ ']',
+ '^',
+ '_',
+ '\\']
+
+
+NORMALIZE_WORD_DICT = {
+    "”": '\\"',
+    "’": "'",
+    "‘": "'",
+    "–": "-",
+    "“": '\\"',
+    "с": "c",
+    "а": "a",
+    "о": "o",
+    "Н": "H",
+    "у": "y",
+    "О": "0",
+    "М": "M",
+    "Α": "A",
+    "А": "A",
+    "Р": "P",
+    "Т": "T",
+    "р": "p",
+    "З": "3",
+    "х": "x",
+    "е": "e",
+    "：": ":",
+    "Η": "H",
+    "（": "(",
+    "К": "K",
+    "Ү": "Y",
+    "б": "6",
+    "․": ".",
+    "В": "B",
+    "С": "C",
+    "Ρ": "P",
+    "і": "i",
+    "г": "r",
+    "Κ": "K",
+    "Х": "X",
+    "Ι": "I",
+    "，": ",",
+    "Τ": "T",
+    "Ј": "J",
+    "У": "y",
+    "๐": "o",
+    "ı": "i",
+    "в": "B",
+    "Β": "B",
+    "һ": "h",
+    "ν": "v",
+    "Τ": "T",
+    "Е": "E",
+    "Ј": "J",
+    "Ι": "I",
+    "Ρ": "P",
+    "У": "y",
+    "І": "I",
+    "Ј": "J",
+    "Ι": "I",
+    "×": "x",
+    "†": "t",
+    "̃": "",
+    " ̣": "",
+    "`": "'",
+    # Latex
+    r"\\left[": r"[",
+    r"\\right]": r"]",
+    r"\\left\\{": r"\\{",
+    r"\\right\\}": r"\\}",
+    r"\\left|": "|",
+    r"\\right|": "|",
+    r"\\left(": r"(",
+    r"\\right)": r")",
+    r"\\left.": r"",
+    r"\\right.": r" ",
+    r"\\cdot": r".",
+    r"\\prime": r"'",
+    r"\\Delta": r"\\triangle",
+    r"\\circ": "o",
+    r"\\bigtriangleup": r"\\triangle",
+    r"\\left ": r" ",
+    r"\\right ": r" ",
+    r"\\le ": r"\\leq ",
+    r"\\ge ": r"\\geq ",
+    r"\\setminus": r"\\backslash",
+    r"$\\bullet$": r"",
+    r"\\therefore": r"",
+    r"\\otimes": r"",
+    r"\\rightarrowI": r"\\rightarrow",
+    r"\\overparen": r"\\widehat",
+    r"\\triangleABC": r"\\triangle ABC",
+    r"\\rightrightarrows": r"\\rightarrow",
+    r"\\top": r"'",
+    r"\\dagger": r"'",
+    r"\\bigoplus": r"Đ",
+    r"\\oplus": r"Đ",
+    r"\\doteq": r"=",
+    r"\\bigcap": r"\\cap",
+    r"\\I": r"I",
+    r"\\l ": r"I",
+    r"\\kappa": r"K",
+    # r"\n": "",
+}
+
+
+CHARACTER_SET = {
+    "$",
+    "\\",
+    " ",
+    "n",
+    "h",
+    "t",
+    "e",
+    "i",
+    "a",
+    "o",
+    "c",
+    ".",
+    "s",
+    "r",
+    "g",
+    "u",
+    "l",
+    "m",
+    "d",
+    "y",
+    "p",
+    "đ",
+    "C",
+    "v",
+    "b",
+    "à",
+    "k",
+    "w",
+    "f",
+    "á",
+    "â",
+    "B",
+    "1",
+    "T",
+    "ư",
+    "A",
+    ")",
+    ",",
+    "D",
+    "Ð",
+    "(",
+    ":",
+    "2",
+    "I",
+    "ệ",
+    "?",
+    "ế",
+    "ạ",
+    "ộ",
+    "3",
+    "ó",
+    "ủ",
+    "ì",
+    "ô",
+    "ả",
+    "ố",
+    "H",
+    "ể",
+    "ớ",
+    "ê",
+    "N",
+    "0",
+    "4",
+    "ề",
+    "í",
+    "x",
+    "5",
+    "ậ",
+    "ị",
+    "M",
+    "ờ",
+    "ấ",
+    "ơ",
+    "S",
+    "'",
+    "ợ",
+    "q",
+    "ọ",
+    "V",
+    "ứ",
+    "-",
+    "Đ",
+    "ú",
+    "ự",
+    "W",
+    "6",
+    "P",
+    "9",
+    "L",
+    "ầ",
+    "7",
+    "8",
+    "ã",
+    "E",
+    "Ẹ",
+    "ă",
+    '"',
+    "ụ",
+    "ữ",
+    "ồ",
+    "G",
+    "ở",
+    "K",
+    "ỉ",
+    "ò",
+    "ẳ",
+    "ắ",
+    "ừ",
+    "ù",
+    "ằ",
+    "R",
+    "O",
+    "ặ",
+    "Q",
+    "ổ",
+    "ĩ",
+    "X",
+    "ỏ",
+    "Y",
+    "ử",
+    "F",
+    "é",
+    "U",
+    "j",
+    "ý",
+    "/",
+    "ẽ",
+    "z",
+    "ỗ",
+    "J",
+    "ễ",
+    "ẩ",
+    "ũ",
+    "Á",
+    "ẹ",
+    "=",
+    "ẫ",
+    "ẻ",
+    "Ẻ",
+    ";",
+    "!",
+    ">",
+    "è",
+    "È",
+    "Ẽ",
+    "[",
+    "]",
+    "*",
+    "À",
+    "Â",
+    "Ẫ",
+    "+",
+    "õ",
+    "Õ",
+    "ỡ",
+    "Ậ",
+    "Ô",
+    "Ỗ",
+    "Ở",
+    "Ỡ",
+    "ỹ",
+    "Ỹ",
+    "^",
+    "ẵ",
+    "ỳ",
+    "Ă",
+    "Ẵ",
+    "|",
+    "Ệ",
+    "Ạ",
+    "Ư",
+    "Ố",
+    "Ý",
+    "Ọ",
+    "Ấ",
+    "ỷ",
+    "Ê",
+    "Ế",
+    "Ầ",
+    "Ề",
+    "Ự",
+    "Í",
+    "Ả",
+    "Ụ",
+    "Ộ",
+    "Z",
+    "Ơ",
+    "}",
+    "Ể",
+    "Ú",
+    "{",
+    "%",
+    "Ị",
+    "Ắ",
+    "_",
+    "Ủ",
+    "Ó",
+    "Ì",
+    "<",
+    "°",
+    "Ớ",
+    "å",
+    "̣",
+    "Ĩ",
+    "~",
+    "Ờ",
+    "Ợ",
+    "̉",
+    "Ỏ",
+    "•",
+    "Ữ",
+    "ā",
+    "&",
+    "Ứ",
+    "Ổ",
+    "Ã",
+    "Ồ",
+    "Ễ",
+    "Ử",
+    "Ẩ",
+    "#",
+    "Ù",
+    "Ò",
+    "É",
+    "ӑ",
+    "\n",
+    "Ặ",
+    "Ũ",
+    "Ỳ",
+    "Ừ",
+    "Ẳ",
+    "Ỷ",
+    "Ằ",
+}

latex2operatortree.py

@@ -0,0 +1,20 @@
+from lxml import etree
+import latex2mathml.converter
+
+
+def mathml_to_operator_tree(node):
+    """Convert MathML to an operator tree."""
+    # If the node is a leaf node, return the operator as a string
+    if len(node) == 0:
+        return node.text
+    # Otherwise, recursively build the operator tree for each child node
+    operator_tree = ""
+    for child in node:
+        operator_tree += str(child.tag).split('}')[-1].replace('m', '') +"(" + str(mathml_to_operator_tree(child)) + ')'
+    return operator_tree
+
+def latex2tree(latex_text):
+    mathml = latex2mathml.converter.convert(latex_text)
+    root = etree.fromstring(mathml.encode())
+    operator_tree = mathml_to_operator_tree(root[0])
+    return operator_tree

test.py

@@ -0,0 +1,15 @@
+import re
+import py_vncorenlp
+from const import *
+from pprint import pprint
+from latex2operatortree import *
+from transformers import AutoTokenizer, AutoModel
+# text = "Trong các hình vẽ sau $y=\dfrac{x+1}{-x+1}$, hình nào biểu diễn đồ thị của hàm số $y=x^3$, $y=x^5$?"
+# pattern = r'\$.*?\$'
+
+# equations = re.findall(pattern, text)
+
+# pprint(latex2tree(text))
+dir = 'code/'
+py_vncorenlp.download_model(save_dir=dir)
+model = py_vncorenlp.VnCoreNLP(save_dir='code/')

tokenizer.py

@@ -0,0 +1,349 @@
+'''
+    BERT Tokenizer custom for Math
+'''
+
+import os
+import re
+from const import *
+from shutil import copyfile #thu vien sao chep tep kem thong tin cua tep
+from typing import List, Optional, Tuple
+
+from transformers.tokenization_utils import PreTrainedTokenizer
+from transformers.utils import logging #log ra thay vi phai in
+
+logger = logging.get_logger(__name__)
+
+VOCAB_FILES_NAMES = {
+    'vocab_file': 'vocab.txt',
+    'merges_file': 'bpe.codes',
+}
+
+PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
+    "vinai/phobert-base": 256,
+    "vinai/phobert-large": 256,
+}
+
+
+def get_pairs(word):
+    '''
+    Return set of symbol pairs in a word.
+
+    Word is represented as tuple of symbols (symbols being variable-length strings).
+    '''
+
+    pairs = set()
+    prev_char = word[0]
+    for char in word[1:]:
+        pairs.add((prev_char, char))
+        prev_char = char
+
+    pairs = set(pairs)
+    return pairs
+
+
+class PhobertTokenizer(PreTrainedTokenizer):
+    '''
+    Construct a PhoBERT tokenizer. Based on Byte-Pair-Encoding.
+    This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to
+    this superclass for more information regarding those methods.
+    
+
+
+    Args:
+        vocab_file (`str`):
+            Path to the vocabulary file.
+        merges_file (`str`):
+            Path to the merges file.
+        bos_token (`st`, *optional*, defaults to `"<s>"`):
+            The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
+            <Tip>
+            When building a sequence using special tokens, this is not the token that is used for the beginning of
+            sequence. The token used is the `cls_token`.
+            </Tip>
+        eos_token (`str`, *optional*, defaults to `"</s>"`):
+            The end of sequence token.
+            <Tip>
+            When building a sequence using special tokens, this is not the token that is used for the end of sequence.
+            The token used is the `sep_token`.
+            </Tip>
+        sep_token (`str`, *optional*, defaults to `"</s>"`):
+            The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for
+            sequence classification or for a text and a question for question answering. It is also used as the last
+            token of a sequence built with special tokens.
+        cls_token (`str`, *optional*, defaults to `"<s>"`):
+            The classifier token which is used when doing sequence classification (classification of the whole sequence
+            instead of per-token classification). It is the first token of the sequence when built with special tokens.
+        unk_token (`str`, *optional*, defaults to `"<unk>"`):
+            The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
+            token instead.
+        pad_token (`str`, *optional*, defaults to `"<pad>"`):
+            The token used for padding, for example when batching sequences of different lengths.
+        mask_token (`str`, *optional*, defaults to `"<mask>"`):
+            The token used for masking values. This is the token used when training this model with masked language
+            modeling. This is the token which the model will try to predict.
+    '''
+    vocab_files_names = VOCAB_FILES_NAMES
+    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
+    model_input_names = ["input_ids", "attention_mask"]
+
+    def __init__(self, 
+                 vocab_file,
+                 merges_file,
+                 bos_token="<s>",
+                 eos_token="</s>",
+                 sep_token="</s>",
+                 cls_token="<s>",
+                 unk_token="<unk>",
+                 pad_token="<pad>",
+                 mask_token="<mask>",
+                 **kwargs):
+        super().__init__(
+                 bos_token=bos_token,
+                 eos_token=eos_token,
+                 unk_token=unk_token,
+                 sep_token=sep_token,
+                 cls_token=cls_token,
+                 pad_token=pad_token,
+                 mask_token=mask_token,
+                 **kwargs,
+        )
+
+        self.vocab_file = vocab_file
+        self.merges_file = merges_file
+
+        self.encoder = {}
+        self.encode[self.bos_token] = 0
+        self.encode[self.pad_token] = 1
+        self.encode[self.eos_token] = 2
+        self.encode[self.unk_token] = 3
+
+        self.add_from_file(vocab_file)
+        self.encoder[self.mask_token] = len(self.encoder)
+
+        self.decoder = {v : k for k, v in self.encoder.items()}
+
+
+        with open(merges_file, encoding="utf-8") as merges_handle:
+            merges = merges_handle.read().split("\n")[:-1]
+        merges = [tuple(merge.split()[:-1]) for merge in merges]
+        self.bpe_ranks = dict(zip(merges, range(len(merges))))
+        self.cache = {}
+
+    def build_inputs_with_special_tokens(self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None) -> List[int]:
+        
+        """
+        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
+        adding special tokens. A PhoBERT sequence has the following format:
+        - single sequence: `<s> X </s>`
+        - pair of sequences: `<s> A </s></s> B </s>`
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs to which the special tokens will be added.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+        Returns:
+            `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
+        """
+
+        if token_ids_1 is None:
+            #cls_token_id -> PretrainedTokenizerBase
+            return [self.cls_token_id]  + token_ids_0 + [self.sep_token_id]
+        cls = [self.cls_token_id]
+        sep = [self.sep_token_id]
+        return cls + token_ids_0 + sep + sep + token_ids_1 + sep
+    
+    
+    def get_special_tokens_mask(self, token_ids_0: List, token_ids_1: Optional[List] = None, already_has_special_tokens: bool = False) -> List[int]:
+
+        """
+        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
+        special tokens using the tokenizer `prepare_for_model` method.
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
+                Whether or not the token list is already formatted with special tokens for the model.
+        Returns:
+            `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
+        """
+
+        if already_has_special_tokens:
+            return super().get_special_tokens_mask(
+                token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
+            )
+
+        if token_ids_1 is None:
+            return [1] + ([0] * len(token_ids_0)) + [1]
+        return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
+    
+
+    def create_token_type_ids_from_sequences(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Create a mask from the two sequences passed to be used in a sequence-pair classification task. PhoBERT does not
+        make use of token type ids, therefore a list of zeros is returned.
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+        Returns:
+            `List[int]`: List of zeros.
+        """
+
+        sep = [self.sep_token_id]
+        cls = [self.cls_token_id]
+
+        if token_ids_1 is None:
+            return len(cls + token_ids_0 + sep) * [0]
+        return len(cls + token_ids_0 + sep + sep + token_ids_1 + sep) * [0]
+
+    @property
+    def vocab_size(self):
+        return len(self.encoder)
+
+    def get_vocab(self):
+        return dict(self.encoder, **self.added_tokens_encoder)
+    
+
+
+    def bpe(self, token):
+        if token in self.cache:
+            return self.cache[token]
+        word = tuple(token)
+        word = tuple(list(word[:-1]) + [word[-1] + "</w>"])
+        pairs = get_pairs(word)
+
+        if not pairs:
+            return token
+
+        while True:
+            bigram = min(pairs, key=lambda pair: self.bpe_ranks.get(pair, float("inf")))
+            if bigram not in self.bpe_ranks:
+                break
+            first, second = bigram
+            new_word = []
+            i = 0
+            while i < len(word):
+                try:
+                    j = word.index(first, i)
+                except ValueError:
+                    new_word.extend(word[i:])
+                    break
+                else:
+                    new_word.extend(word[i:j])
+                    i = j
+
+                if word[i] == first and i < len(word) - 1 and word[i + 1] == second:
+                    new_word.append(first + second)
+                    i += 2
+                else:
+                    new_word.append(word[i])
+                    i += 1
+            new_word = tuple(new_word)
+            word = new_word
+            if len(word) == 1:
+                break
+            else:
+                pairs = get_pairs(word)
+        word = "@@ ".join(word)
+        word = word[:-4]
+        self.cache[token] = word
+        return word
+
+    def _tokenize(self, text):
+        """Tokenize a string."""
+        split_tokens = []
+
+        words = re.findall(r"\S+\n?", text)
+
+        for token in words:
+            split_tokens.extend([t for t in self.bpe(token).split(" ")])
+        return split_tokens
+
+    def _convert_token_to_id(self, token):
+        """Converts a token (str) in an id using the vocab."""
+        return self.encoder.get(token, self.encoder.get(self.unk_token))
+
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        return self.decoder.get(index, self.unk_token)
+
+    def convert_tokens_to_string(self, tokens):
+        """Converts a sequence of tokens (string) in a single string."""
+        out_string = " ".join(tokens).replace("@@ ", "").strip()
+        return out_string
+
+    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
+        if not os.path.isdir(save_directory):
+            logger.error(f"Vocabulary path ({save_directory}) should be a directory.")
+            return
+
+        out_vocab_file = os.path.join(
+            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
+        )
+
+        if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
+            copyfile(self.vocab_file, out_vocab_file)
+        elif not os.path.isfile(self.vocab_file):
+            with open(out_vocab_file, "w", encoding="utf-8") as fp:
+                for token, value in self.encoder.items():
+                    if token not in self.all_special_tokens:
+                        fp.write(f"{str(token)} 1\n")
+
+        out_merges_file = os.path.join(
+            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["merges_file"]
+        )
+
+        if os.path.abspath(self.merges_file) != os.path.abspath(out_merges_file) and os.path.isfile(self.merges_file):
+            copyfile(self.merges_file, out_merges_file)
+        elif not os.path.isfile(self.merges_file):
+            index = 0
+            with open(out_merges_file, "w", encoding="utf-8") as writer:
+                for bpe_tokens, token_index in sorted(self.bpe_ranks.items(), key=lambda kv: kv[1]):
+                    if index != token_index:
+                        logger.warning(
+                            f"Saving vocabulary to {out_merges_file}: BPE merge indices are not consecutive."
+                            " Please check that the tokenizer is not corrupted!"
+                        )
+                        index = token_index
+                    writer.write(" ".join(bpe_tokens) + " 1\n")
+                    index += 1
+
+        return (out_vocab_file, out_merges_file)
+
+    # def decode(self, token_ids, skip_special_tokens=False, clean_up_tokenization_spaces=True):
+    #     filtered_tokens = ' '.join(self.convert_ids_to_tokens(token_ids, skip_special_tokens=skip_special_tokens))
+    #     tokens_generated_so_far = re.sub('(@@ )', '', string=filtered_tokens)
+    #     tokens_generated_so_far = re.sub('(@@ ?$)', '', string=tokens_generated_so_far)
+    #     return ''.join(tokens_generated_so_far)
+
+
+
+    def add_from_file(self, f):
+        """
+        Loads a pre-existing dictionary from a text file and adds its symbols to this instance.
+        """
+        if isinstance(f, str):
+            try:
+                with open(f, "r", encoding="utf-8") as fd:
+                    self.add_from_file(fd)
+            except FileNotFoundError as fnfe:
+                raise fnfe
+            except UnicodeError:
+                raise Exception(f"Incorrect encoding detected in {f}, please rebuild the dataset")
+            return
+
+        lines = f.readlines()
+        for lineTmp in lines:
+            line = lineTmp.strip()
+            idx = line.rfind(" ")
+            if idx == -1:
+                raise ValueError("Incorrect dictionary format, expected '<token> <cnt>'")
+            word = line[:idx]
+            self.encoder[word] = len(self.encoder)
+        for word in LATEX_VOC:
+            self.encoder[word] = len(self.encoder)