-#! /usr/bin/env python
# -*- coding: utf-8 -*-
# file csv2lyx.py
# author Hartmut Haase
# author José Matos
-
# Full author contact details are available in file CREDITS
# This script reads a csv-table (file name.csv) and converts it into
sys.stderr.write(message + '\n')
sys.exit(1)
+header = """#csv2lyx created this file. For more info see http://www.lyx.org/
+\\lyxformat 413
+\\begin_document
+\\begin_header
+\\textclass article
+\\use_default_options true
+\\maintain_unincluded_children false
+\\language english
+\\language_package default
+\\inputencoding auto
+\\fontencoding global
+\\font_roman default
+\\font_sans default
+\\font_typewriter default
+\\font_default_family default
+\\use_non_tex_fonts false
+\\font_sc false
+\\font_osf false
+\\font_sf_scale 100
+\\font_tt_scale 100
+
+\\graphics default
+\\default_output_format default
+\\output_sync 0
+\\bibtex_command default
+\\index_command default
+\\paperfontsize default
+\\use_hyperref false
+\\papersize default
+\\use_geometry false
+\\use_amsmath 1
+\\use_esint 1
+\\use_mhchem 1
+\\use_mathdots 1
+\\cite_engine basic
+\\use_bibtopic false
+\\use_indices false
+\\paperorientation portrait
+\\suppress_date false
+\\use_refstyle 1
+\\index Index
+\\shortcut idx
+\\color #008000
+\\end_index
+\\secnumdepth 3
+\\tocdepth 3
+\\paragraph_separation indent
+\\paragraph_indentation default
+\\quotes_language english
+\\papercolumns 1
+\\papersides 1
+\\paperpagestyle default
+\\tracking_changes false
+\\output_changes false
+\\html_math_output 0
+\\html_css_as_file 0
+\\html_be_strict false
+\\end_header
+
+\\begin_body
+
+\\begin_layout Standard
+\\begin_inset Tabular
+<lyxtabular version="3" rows="%d" columns="%d">
+<features tabularvalignment="middle">
+"""
+
+cell = """<cell alignment="left" valignment="top" usebox="none">
+\\begin_inset Text
+
+\\begin_layout Plain Layout
+%s
+\\end_layout
+
+\\end_inset
+</cell>"""
+
+footer = """</lyxtabular>
+
+\\end_inset
+
+
+\\end_layout
+
+\\end_body
+\\end_document
+"""
+
# processing command line options
# delegate this to standard module optparse
args = {}
-args["usage"] = "Usage: csv2lyx [options] mycsvfile mytmptable.lyx"
+args["usage"] = "Usage: csv2lyx [options] csvfile [file.lyx]"
-args["description"] = """This script creates a LyX document containing a table
-from a comma-separated-value file. The LyX file has format 276
-and can be opened with LyX 1.5.0 and newer.
+args["description"] = """This script creates a LyX document containing a table created from a
+comma-separated-value (CSV) file. The resulting LyX file can be opened
+with LyX 1.5.0 or any later version.
+If no options are given csv2lyx will try to infer the CSV type of the csvfile,
"""
parser = optparse.OptionParser(**args)
-parser.set_defaults(excel = 'n', column_sep = 'n', guess_sep = False)
-parser.add_option("-e", "--excel",
- help="""'character' Excel type, default is 'n'
+parser.set_defaults(excel ='', column_sep = '')
+parser.add_option("-e", "--excel", metavar ="CHAR",
+ help = """CHAR corresponds to a CSV type:
'e': Excel-generated CSV file
't': Excel-generated TAB-delimited CSV file""")
-parser.add_option("-s", "--separator", dest="column_sep",
- help= "column separator, default is ','")
-parser.add_option("-g", "--guess-sep", action="store_true",
- help = "guess the columns separator")
+parser.add_option("-s", "--separator", dest = "column_sep",
+ help = """column separator
+ 't' means Tab""")
-group = optparse.OptionGroup(parser, "Remarks", """If your .csv file contains special characters (e. g. umlauts,
+group = optparse.OptionGroup(parser, "Remarks", """If your CSV file contains special characters (e. g. umlauts,
accented letters, etc.) make sure it is coded in UTF-8 (unicode).
- Else LyX will loose some cell contents. If your .csv file was not written according to the "Common Format and MIME Type for Comma-Separated Values (CSV) Files" (http://tools.ietf.org/html/rfc4180) there may be unexpected results.""")
+ Else LyX will loose some cell contents. If your CSV file was not written according to the "Common Format and MIME Type for Comma-Separated Values (CSV) Files" (http://tools.ietf.org/html/rfc4180) there may be unexpected results.""")
parser.add_option_group(group)
(options, args) = parser.parse_args()
if len(args) == 1:
infile = args[0]
fout = sys.stdout
-elif len(args) ==2:
+elif len(args) == 2:
infile = args[0]
fout = open(args[1], 'w')
else:
if not os.path.exists(infile):
error('File "%s" not found.' % infile)
-dialects = {'n' : None, 'e' : 'excel', 't' : 'excel-tab'}
+dialects = {'' : None, 'e' : 'excel', 't' : 'excel-tab'}
if options.excel not in dialects:
parser.print_help()
sys.exit(1)
-dialect= dialects[options.excel]
+dialect = dialects[options.excel]
+
+# Set Tab, if necessary
+if options.column_sep == 't':
+ options.column_sep = "\t"
# when no special column separator is given, try to detect it:
-if options.column_sep == 'n':
- options.guess_sep = 'True'
-print options.column_sep, options.guess_sep
-if options.guess_sep:
+if options.column_sep and dialect :
+ reader = csv.reader(open(infile, "rU"), dialect = dialect, delimiter = options.column_sep)
+else:
guesser = csv.Sniffer()
- input_file = "".join(open(infile,'rb').readlines())
+ input_file = "".join(open(infile,'rU').readlines())
try:
dialect = guesser.sniff(input_file)
- print 'found:', dialect.delimiter
- reader = csv.reader(open(infile, "rb"), dialect= dialect)
+ reader = csv.reader(open(infile, "rU"), dialect = dialect)
except:
- print 'error, using ,'
- reader = csv.reader(open(infile, "rb"), dialect= dialect, delimiter=',')
-else:
- reader = csv.reader(open(infile, "rb"), dialect= dialect, delimiter=options.column_sep)
+ # older versions (python < 2.5) of csv have problems (bugs)
+ # that is why we try harder to get a result, this should work on most cases
+ # as it assumes that the separator is a comma (the c in csv :-) )
+ try:
+ reader = csv.reader(open(infile, "rU"), dialect = dialect, delimiter = ',')
+ except:
+ reader = csv.reader(open(infile, "rU"), delimiter = ',')
# read input
num_cols = 1 # max columns
num_cols = max(num_cols, len(row))
rows.append(row)
-num_rows = reader.line_num # number of lines
+num_rows = len(rows) # number of lines
# create a LyX file
#####################
# write first part
####################
-fout.write("""#csv2lyx created this file
-\lyxformat 276
-\\begin_document
-\\begin_header
-\\textclass article
-\\inputencoding auto
-\\font_roman default
-\\font_sans default
-\\font_typewriter default
-\\font_default_family default
-\\font_sc false
-\\font_osf false
-\\font_sf_scale 100
-\\font_tt_scale 100
-\\graphics default
-\\paperfontsize default
-\\papersize default
-\\use_geometry false
-\\use_amsmath 1
-\\use_esint 0
-\\cite_engine basic
-\\use_bibtopic false
-\\paperorientation portrait
-\\secnumdepth 3
-\\tocdepth 3
-\\paragraph_separation indent
-\\defskip medskip
-\\papercolumns 1
-\\papersides 1
-\\paperpagestyle default
-\\tracking_changes false
-\\output_changes false
-\\end_header
-
-\\begin_body
+fout.write(header % (num_rows, num_cols))
-\\begin_layout Standard
-\\align left
-\\begin_inset Tabular
-""")
-fout.write('<lyxtabular version="3" rows=\"' + str(num_rows) + '\" columns=\"' + str(num_cols) + '\">\n')
-fout.write('<features>\n')
#####################
# write table
####################
-i = 0
-while i < num_cols:
+for i in range(num_cols):
fout.write('<column alignment="left" valignment="top" width="0pt">\n')
- i += 1
-j = 0
-while j < num_rows:
- fout.write('<row>\n')
- num_cols_2 = len(rows[j]) # columns in current row
- #print j, ': ' , rows[j]
-############################
-# write contents of one line
-############################
- i = 0
- while i < num_cols_2:
- fout.write("""<cell alignment="left" valignment="top" usebox="none">
-\\begin_inset Text
-
-\\begin_layout Standard\n""")
- #print rows[j][i]
- fout.write(rows[j][i])
- fout.write('\n\\end_layout\n\n\\end_inset\n</cell>\n')
- i += 1
-# If row has less columns than num_cols
- if num_cols_2 < num_cols:
- while i < num_cols:
- fout.write("""<cell alignment="left" valignment="top" usebox="none">
-\\begin_inset Text
-\\begin_layout Standard\n""")
- fout.write(' ')
- fout.write('\n\\end_layout\n\n\\end_inset\n</cell>\n')
- i += 1
- fout.write('</row>\n')
- j += 1
-#####################
-# write last part
-####################
-fout.write("""</lyxtabular>
+for j in range(num_rows):
+ row = ['<row>']
-\\end_inset
+ ############################
+ # write contents of one line
+ ############################
+ for i in range(len(rows[j])):
+ row.append( cell % rows[j][i].replace('\\','\\backslash\n'))
+ # If row has less columns than num_cols fill with blank entries
+ for i in range(len(rows[j]), num_cols):
+ row.append(cell % " ")
-\\end_layout
+ fout.write("\n".join(row) + '\n</row>\n')
-\\end_body
-\\end_document\n""")
+#####################
+# write last part
+####################
+fout.write(footer)
# close the LyX file
fout.close()
projects / lyx.git / blobdiff