#!/usr/bin/python import sys from enum import Enum class Table: def __init__(self, header, columns, matrix): self.header = header self.columns = columns self.matrix = matrix self.matrix_fix = [] self.table = '' def get(self, row, column): if row > column: return self.get(column, row) return self.matrix[row][column - row] def get_row(self, row): return self.matrix[row] def __str__(self): return self.__unicode__() def fixmatrix(self): self.matrix_fix = self.matrix for i in range(0, len(self.matrix)): for j in range(0, len(self.matrix[i])): if self.matrix[i][j] == ' ': self.matrix_fix[i][j] = get_ride_of_latex(self.matrix[j - 1][i + 1]) # print(i,j, table.matrix[j-1][i+1]) else: # print(i,j, get_ride_of_latex(table.matrix[i][j])) self.matrix_fix[i][j] = get_ride_of_latex(self.matrix[i][j]) def get_string(self): s = '*data: x : ' for i in range(1, len(self.matrix_fix[0]) - 1): s += "y :" s += " y " self.table += s + '\n' for i in range(0, len(self.matrix_fix)): s = '' s += self.columns[i + 1] + " : " for j in range(1, len(self.matrix_fix[i])): # print('a',self.matrix_fix[j-1][i+1]) s += get_ride_of_latex(self.matrix_fix[j - 1][i + 1]) + ' : ' self.table += s + '\n' # self.table+= \ def __unicode__(self): dupa=":".join(self.columns) dupa=dupa.replace(': ', '', 1) #print(dupa) return """*dataset: *location: Appendix F *dscomment: %s *yheader: %s *data CHANGEME %s *dataend: """ % (self.header, dupa, self.table) class TableBuilder: def __init__(self): self.header = None self.columns = None self.matrix = [] self.matrix_fix = [] def add_row(self, row): self.matrix.append(row) def build(self): return Table(self.header, self.columns, self.matrix) def parse_table_header(self, line): line[:-2].split('&') line=line.replace('\subsection*{', '')[:-1] line=line.replace(r'\gevgevcccc', r'~\rm GeV/c^4') line=line.replace(r'\boldmath{', r'') line=line.replace(r'4$}', r'4$') return line.replace('\subsection*{', '')[:-1] def parse_columns_names(self, line): print('wtf ', line) line = line.replace(': ', '', 4) a = (line[:-4].split('&')) #a = a.replace(': ', '', 4) print('a',a) return a # line[:-2].split('&') def parse_row(self, line): return line[:-5].split('&') def fixmatrix(self): self.matrix_fix = self.matrix for i in range(0, len(self.matrix)): for j in range(0, len(self.matrix[i])): if self.matrix[i][j] == ' ': self.matrix_fix[i][j] = get_ride_of_latex(self.matrix[j - 1][i + 1]) # print(i,j, table.matrix[j-1][i+1]) else: # print(i,j, get_ride_of_latex(table.matrix[i][j])) self.matrix_fix[i][j] = get_ride_of_latex(self.matrix[i][j]) class ParserStateEnum(Enum): BEFORE_TABLE = 1 READING_COLUMNS_NAMES = 2 READING_TABLE = 3 DONE = 4 class TableParser: def __init__(self): self.state = ParserStateEnum.BEFORE_TABLE self.builder = TableBuilder() self.table = None def feed_line(self, line): if self.state is ParserStateEnum.BEFORE_TABLE: self.feed_line_before_table(line) elif self.state is ParserStateEnum.READING_COLUMNS_NAMES: self.feed_line_columns_names(line) else: self.feed_line_reading_table(line) def feed_line_before_table(self, line): if self.is_table_header(line): self.builder.header = self.builder.parse_table_header(line) elif self.is_table_begin(line): self.state = ParserStateEnum.READING_COLUMNS_NAMES def feed_line_columns_names(self, line): if line: self.builder.columns = self.builder.parse_columns_names(line) self.state = ParserStateEnum.READING_TABLE def feed_line_reading_table(self, line): if self.is_table_end(line): self.build() elif not self.is_hline(line): self.builder.add_row(self.builder.parse_row(line)) def is_hline(self, line): return line.startswith(r'\hline') def is_table_header(self, line): return line.startswith(r'\subsection') def is_table_begin(self, line): return line.startswith(r'\begin{tabular}') def is_table_end(self, line): return line.startswith(r'\end{tabular}') def build(self): self.state = ParserStateEnum.DONE self.table = self.builder.build() def get_ride_of_latex(line): line2 = line line2 = line2.replace(r"\\rm", r"\rm") line2 = line2.replace(r"\\", "") line2 = line2.replace(r'$', '') line2 = line2.replace(r'\ ', '') line2 = line2.replace(r'\ ', '') #line2 = line2.replace(r'\gevgevcccc', 'GeV/c^4') return line2 def parse_file(fd): tables = [] tables_fix = [] parser = TableParser() for line in fd.readlines(): parser.feed_line(line) if parser.state is ParserStateEnum.DONE: tables.append(parser.table) parser = TableParser() for table in tables: table.fixmatrix() table.get_string() print(table) # print(table.matrix_fix) ''' for i in range(0,len(table.matrix)): for j in range(0,len(table.matrix[i])): if table.matrix[i][j] == ' ': print(i,j, get_ride_of_latex(table.matrix[j-1][i+1])) else: print(i,j, get_ride_of_latex(table.matrix[i][j])) #get_ride_of_latex(table.get(i,j))) ''' # print(tables[0]) # print(tables[0].get(0,1,9)) fd = open('appendix_bootstrap_correlations.tex', 'r') parse_file(fd)