/usr/share/runxlrd/runxlrd.py is in python-xlrd 0.6.1-2.
This file is owned by root:root, with mode 0o755.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 | #!/usr/bin/python
# -*- coding: cp1252 -*-
# <p>Copyright (C) 2005-2007 Stephen John Machin, Lingfo Pty Ltd</p>
# <p>This script is part of the xlrd package, which is released under a
# BSD-style licence.</p>
# 2007-06-10 SJM Removed reference to removed "trimming" option-value.
# 2007-06-10 SJM Added documentation of commands.
# 2007-06-10 SJM Changed cmds: dump -> biff_dump, count_records -> biff_count.
cmd_doc = """
Commands:
2rows Print the contents of first and last row in each sheet
3rows Print the contents of first, second and last row in each sheet
bench Same as "show", but doesn't print -- for profiling
biff_count[1] Print a count of each type of BIFF record in the file
biff_dump[1] Print a dump (char and hex) of the BIFF records in the file
hdr Mini-overview of file (no per-sheet information)
hotshot Do a hotshot profile run e.g. ... -f1 hotshot bench bigfile*.xls
labels Dump of sheet.col_label_ranges and ...row... for each sheet
name_dump Dump of each object in book.name_obj_list
names Print brief information for each NAME record
ov Overview of file
profile Like "hotshot", but uses cProfile
show Print the contents of all rows in each sheet
version[0] Print versions of xlrd and Python and exit
xfc Print "XF counts" and cell-type counts -- see code for details
[0] means no file arg
[1] means only one file arg i.e. no glob.glob pattern
"""
options = None
if __name__ == "__main__":
PSYCO = 0
import xlrd
import sys, time, glob, traceback, pprint, gc
null_cell = xlrd.empty_cell
def show_row(bk, sh, rowx, colrange, printit):
if printit: print
if bk.formatting_info:
for colx, ty, val, cxfx in get_row_data(bk, sh, rowx, colrange):
if printit:
print "cell %s%d: type=%d, data: %r, xfx: %s" \
% (xlrd.colname(colx), rowx+1, ty, val, cxfx)
else:
for colx, ty, val, _unused in get_row_data(bk, sh, rowx, colrange):
if printit:
print "cell %s%d: type=%d, data: %r" % (xlrd.colname(colx), rowx+1, ty, val)
def get_row_data(bk, sh, rowx, colrange):
result = []
dmode = bk.datemode
ctys = sh.row_types(rowx)
cvals = sh.row_values(rowx)
for colx in colrange:
cty = ctys[colx]
cval = cvals[colx]
if bk.formatting_info:
cxfx = str(sh.cell_xf_index(rowx, colx))
else:
cxfx = ''
if cty == xlrd.XL_CELL_DATE:
try:
showval = xlrd.xldate_as_tuple(cval, dmode)
except xlrd.XLDateError:
e1, e2 = sys.exc_info()[:2]
showval = "%s:%s" % (e1.__name__, e2)
cty = xlrd.XL_CELL_ERROR
elif cty == xlrd.XL_CELL_ERROR:
showval = xlrd.error_text_from_code.get(cval, '<Unknown error code 0x%02x>' % cval)
else:
showval = cval
result.append((colx, cty, showval, cxfx))
return result
def bk_header(bk):
print
print "BIFF version: %s; datemode: %s" \
% (xlrd.biff_text_from_num[bk.biff_version], bk.datemode)
print "codepage: %r (encoding: %s); countries: %r" \
% (bk.codepage, bk.encoding, bk.countries)
print "Last saved by: %r" % bk.user_name
print "Number of data sheets: %d" % bk.nsheets
print "Pickleable: %d; Use mmap: %d; Formatting: %d" \
% (bk.pickleable, bk.use_mmap, bk.formatting_info)
print "FORMATs: %d, FONTs: %d, XFs: %d" \
% (len(bk.format_list), len(bk.font_list), len(bk.raw_xf_list))
print "Load time: %.2f seconds (stage 1) %.2f seconds (stage 2)" \
% (bk.load_time_stage_1, bk.load_time_stage_2)
print
def show_names(bk, dump=0):
bk_header(bk)
if bk.biff_version < 50:
print "Names not extracted in this BIFF version"
return
nlist = bk.name_obj_list
print "Name list: %d entries" % len(nlist)
for nobj in nlist:
if dump:
nobj.dump(sys.stdout,
header="\n=== Dump of name_obj_list[%d] ===" % nobj.name_index)
else:
print "[%d]\tName:%r macro:%r scope:%d\n\tresult:%r\n" \
% (nobj.name_index, nobj.name, nobj.macro, nobj.scope, nobj.result)
def print_labels(sh, labs, title):
if not labs:return
for rlo, rhi, clo, chi in labs:
print "%s label range %s:%s contains:" \
% (title, xlrd.cellname(rlo, clo), xlrd.cellname(rhi-1, chi-1))
for rx in xrange(rlo, rhi):
for cx in xrange(clo, chi):
print " %s: %r" % (xlrd.cellname(rx, cx), sh.cell_value(rx, cx))
def show_labels(bk):
# bk_header(bk)
hdr = 0
for shx in range(bk.nsheets):
sh = bk.sheet_by_index(shx)
clabs = sh.col_label_ranges
rlabs = sh.row_label_ranges
if clabs or rlabs:
if not hdr:
bk_header(bk)
hdr = 1
print "sheet %d: name = %r; nrows = %d; ncols = %d" % \
(shx, sh.name, sh.nrows, sh.ncols)
print_labels(sh, clabs, 'Col')
print_labels(sh, rlabs, 'Row')
def show(bk, nshow=65535, printit=1):
bk_header(bk)
if 0:
rclist = xlrd.sheet.rc_stats.items()
rclist.sort()
print "rc stats"
for k, v in rclist:
print "0x%04x %7d" % (k, v)
if options.onesheet:
try:
shx = int(options.onesheet)
except ValueError:
shx = bk.sheet_by_name(options.onesheet).number
shxrange = [shx]
else:
shxrange = range(bk.nsheets)
# print "shxrange", shxrange
for shx in shxrange:
sh = bk.sheet_by_index(shx)
nrows, ncols = sh.nrows, sh.ncols
colrange = range(ncols)
anshow = min(nshow, nrows)
print "sheet %d: name = %r; nrows = %d; ncols = %d" % \
(shx, sh.name, sh.nrows, sh.ncols)
if nrows and ncols:
# Attempt to access the RHS corners
sh.row_types(0)[ncols-1]
sh.row_values(0)[ncols-1]
sh.row_types(nrows-1)[ncols-1]
sh.row_values(nrows-1)[ncols-1]
for rowx in xrange(anshow-1):
if not printit and rowx % 10000 == 1 and rowx > 1:
print "done %d rows" % (rowx-1,)
show_row(bk, sh, rowx, colrange, printit)
if anshow and nrows:
show_row(bk, sh, nrows-1, colrange, printit)
print
def count_xfs(bk):
bk_header(bk)
for shx in range(bk.nsheets):
sh = bk.sheet_by_index(shx)
nrows, ncols = sh.nrows, sh.ncols
print "sheet %d: name = %r; nrows = %d; ncols = %d" % \
(shx, sh.name, sh.nrows, sh.ncols)
if nrows and ncols:
# Attempt to access the RHS corners
sh.row_types(0)[ncols-1]
sh.row_values(0)[ncols-1]
sh.row_types(nrows-1)[ncols-1]
sh.row_values(nrows-1)[ncols-1]
# Access all xfindexes to force gathering stats
type_stats = [0, 0, 0, 0, 0, 0, 0]
for colx in xrange(ncols):
for rowx in xrange(nrows):
xfx = sh.cell_xf_index(rowx, colx)
assert xfx >= 0
cty = sh.cell_type(rowx, colx)
type_stats[cty] += 1
print "XF stats", sh._xf_index_stats
print "type stats", type_stats
print
def main(cmd_args):
import optparse
global options
usage = "\n%prog [options] command [input-file-patterns]\n" + cmd_doc
oparser = optparse.OptionParser(usage)
oparser.add_option(
"-l", "--logfilename",
default="",
help="contains error messages")
oparser.add_option(
"-v", "--verbosity",
type="int", default=0,
help="level of information and diagnostics provided")
oparser.add_option(
"-p", "--pickleable",
type="int", default=1,
help="1: ensure Book object is pickleable (default); 0: don't bother")
oparser.add_option(
"-m", "--mmap",
type="int", default=-1,
help="1: use mmap; 0: don't use mmap; -1: accept heuristic")
oparser.add_option(
"-e", "--encoding",
default="",
help="encoding override")
oparser.add_option(
"-f", "--formatting",
type="int", default=0,
help="0 (default): no fmt info\n"
"1: fmt info (all cells)\n"
)
oparser.add_option(
"-g", "--gc",
type="int", default=0,
help="0: auto gc enabled; 1: auto gc disabled, manual collect after each file; 2: no gc")
oparser.add_option(
"-s", "--onesheet",
default="",
help="restrict output to this sheet (name or index)")
options, args = oparser.parse_args(cmd_args)
if len(args) == 1 and args[0] in ("version", ):
pass
elif len(args) < 2:
oparser.error("Expected at least 2 args, found %d" % len(args))
cmd = args[0]
xlrd_version = getattr(xlrd, "__VERSION__", "unknown; before 0.5")
if cmd == 'biff_dump':
xlrd.dump(args[1])
sys.exit(0)
if cmd == 'biff_count':
xlrd.count_records(args[1])
sys.exit(0)
if cmd == 'version':
print "xlrd: %s, from %s" % (xlrd_version, xlrd.__file__)
print "Python:", sys.version
sys.exit(0)
if options.logfilename:
logfile = open(options.logfilename, 'w')
else:
logfile = sys.stdout
mmap_opt = options.mmap
mmap_arg = xlrd.USE_MMAP
if mmap_opt in (1, 0):
mmap_arg = mmap_opt
elif mmap_opt != -1:
print 'Unexpected value (%r) for mmap option -- assuming default' % mmap_opt
fmt_opt = options.formatting
gc_mode = options.gc
if gc_mode:
gc.disable()
for pattern in args[1:]:
for fname in glob.glob(pattern):
print >> logfile, "\n=== File: %s ===" % fname
if gc_mode == 1:
n_unreachable = gc.collect()
if n_unreachable:
print >> logfile, "GC before open:", n_unreachable, "unreachable objects"
try:
t0 = time.time()
bk = xlrd.open_workbook(fname,
verbosity=options.verbosity, logfile=logfile,
pickleable=options.pickleable, use_mmap=mmap_arg,
encoding_override=options.encoding,
formatting_info=fmt_opt,
)
t1 = time.time()
print >> logfile, "Open took %.2f seconds" % (t1-t0,)
except xlrd.XLRDError:
print >> logfile, "*** Open failed: %s: %s" % sys.exc_info()[:2]
continue
except KeyboardInterrupt:
print >> logfile, "*** KeyboardInterrupt ***"
traceback.print_exc(file=logfile)
sys.exit(1)
except:
print >> logfile, "*** Open failed ***"
traceback.print_exc(file=logfile)
continue
t0 = time.time()
if cmd == 'hdr':
bk_header(bk)
elif cmd == 'ov': # OverView
show(bk, 0)
elif cmd == 'show': # all rows
show(bk)
elif cmd == '2rows': # first row and last row
show(bk, 2)
elif cmd == '3rows': # first row, 2nd row and last row
show(bk, 3)
elif cmd == 'bench':
show(bk, printit=False)
elif cmd == 'names': # named reference list
show_names(bk)
elif cmd == 'name_dump': # named reference list
show_names(bk, dump=1)
elif cmd == 'labels':
show_labels(bk)
elif cmd == 'xfc':
count_xfs(bk)
else:
print >> logfile, "*** Unknown command <%s>" % cmd
sys.exit(1)
del bk
if gc_mode == 1:
n_unreachable = gc.collect()
if n_unreachable:
print >> logfile, "GC post cmd:", fname, "->", n_unreachable, "unreachable objects"
t1 = time.time()
print >> logfile, "\ncommand took %.2f seconds\n" % (t1-t0,)
return None
av = sys.argv[1:]
if not av:
main(av)
firstarg = av[0].lower()
if firstarg == "hotshot":
import hotshot, hotshot.stats
av = av[1:]
prof_log_name = "XXXX.prof"
prof = hotshot.Profile(prof_log_name)
# benchtime, result = prof.runcall(main, *av)
result = prof.runcall(main, *(av, ))
print "result", repr(result)
prof.close()
stats = hotshot.stats.load(prof_log_name)
stats.strip_dirs()
stats.sort_stats('time', 'calls')
stats.print_stats(20)
elif firstarg == "profile":
import cProfile
av = av[1:]
cProfile.run('main(av)', 'YYYY.prof')
import pstats
p = pstats.Stats('YYYY.prof')
p.strip_dirs().sort_stats('cumulative').print_stats(30)
else:
main(av)
|