#4 version tagcount_ls_jim_29.12.24.txt

issues/issue4/adjust_tooltip.py

@@ -0,0 +1,93 @@
+# coding=utf-8
+""" adjust_tooltip.py
+"""
+from __future__ import print_function
+import sys, re,codecs
+
+def read_lines(filein):
+ with codecs.open(filein,encoding='utf-8',mode='r') as f:
+  lines = [x.rstrip('\r\n') for x in f]
+ return lines
+
+def write_recs(fileout,recs):
+ outrecs = []
+ for rec in recs:
+  outarr = []
+  if rec.newtooltip == None:
+   out = rec.line # no change
+  else:
+   parts0 = rec.parts0
+   parts0[3] = rec.newtooltip
+   out = '\t' . join(parts0)
+  outarr.append(out)
+  outrecs.append(outarr)
+ with codecs.open(fileout,"w","utf-8") as f:
+  for outarr in outrecs:
+   for out in outarr:
+    f.write(out+'\n')
+ print(len(recs),"records written to",fileout)
+
+
+class Tagcount:
+ def __init__(self,line):
+  self.line = line
+  parts = line.split('\t') # tab-separated values
+  self.parts0 = parts
+  self.status =  len(parts) == 4
+  self.parts = [p.strip() for p in parts]
+  self.countstr, self.lsstr,self.ls,self.tooltip = self.parts
+  assert self.lsstr in ('ls','lsfm','lsfm?')
+  self.newtooltip = None
+
+def init_tagcount(filein):
+ lines = read_lines(filein)
+ recs = [Tagcount(line) for line in lines]
+ return recs
+
+def generate_changes(lines):
+ group = None
+ for iline,line in enumerate(lines):
+  m = re.search('old: (.*)$',line)
+  if m != None:
+   old = m.group(1)
+   continue
+  m = re.search('new: (.*)$',line)
+  if m != None:
+   new = m.group(1)
+   group = (old,new)
+   yield group
+   old = None
+
+def init_changes(filein):
+ lines = read_lines(filein)
+ changes = list(generate_changes(lines))
+ print(len(changes),"changes read from",filein)
+ return changes
+
+def apply_changes(recs,changes):
+ d = {} # make changes a dictionary
+ for change in changes:
+  old,new = change
+  if old in d:
+   print('duplicate change found')
+   exit(1)
+  d[old] = new
+ n = 0
+ for rec in recs:
+  tip = rec.tooltip
+  if tip in d:
+   newtip = d[tip]
+   rec.newtooltip = newtip
+   n = n + 1
+ print(n,"records with tooltip change")
+
+if __name__=="__main__":
+ filein = sys.argv[1] # tagcount_ls_1.txt
+ filein1 = sys.argv[2] # tooltip changes
+ fileout = sys.argv[3] # both files written to facilitate comparison
+ #fileout1 = sys.argv[4] # change stats
+
+ recs = init_tagcount(filein)
+ changes = init_changes(filein1)
+ apply_changes(recs,changes)  # newtooltip attribute computed
+ write_recs(fileout,recs)

issues/issue4/adjust_tooltip_anna.txt

@@ -0,0 +1,8 @@
+old: ;; Śikṣāsamuccaya, A Compendium of Buddhist Doctrine / transl. C.Bendall and  W.H.D.Rouse. London: John Murray, 1922.
+new: Śikṣāsamuccaya, ed. Bendall, St. Petersburg, 1897—1902; transl. Bendall and Rouse, London, 1922.
+old: ;; Avadāna-śataka, ed. Speyer J. S., 2 vols., St. Petersburg, 1902, 1906.
+new: Avadāna-śataka, ed. Speyer, 2 vols., St. Petersburg, 1902, 1906; transl. Feer, Annales du Musée Guimet 18 (1891).
+old: ;; The Divyāvadāna: A Collection of Early Buddhist Legends, ed. E.B.Cowell and R.A.Neil, Cambridge, 1886.
+new: Divyāvadāna, ed. Cowell and Neil, Cambridge, 1886.
+old: ;; W.KirfelDie, Kosmographie der Inder: nach den Quellen dargestellt / Bonn–Leipzig: Kurt Schroeder, 1920.
+new: Kosmographie der Inder.

issues/issue4/compare_tagcount_ls.py

@@ -0,0 +1,133 @@
+# coding=utf-8
+""" compare_tagcount_ls.py
+"""
+from __future__ import print_function
+import sys, re,codecs
+
+def read_lines(filein):
+ with codecs.open(filein,encoding='utf-8',mode='r') as f:
+  lines = [x.rstrip('\r\n') for x in f]
+ return lines
+
+def write_diffs_check3(fileout,diffs):
+ outrecs = []
+ for idiff,diff in enumerate(diffs):
+  outarr = []
+  rec1,rec2,irec = diff
+  outarr.append('; diff %s at line %s' %(idiff+1,irec+1))
+  outarr.append('; cdsl')
+  outarr.append(rec1.line)
+  outarr.append('; anna')
+  outarr.append(rec2.line)
+  outarr.append('; ------------------------------------------------------------')
+  outrecs.append(outarr)
+ with codecs.open(fileout,"w","utf-8") as f:
+  for outarr in outrecs:
+   for out in outarr:
+    f.write(out+'\n')
+ print(len(diffs),"difference records written to",fileout)
+
+def write_compare(fileout,recs1,recs2):
+ outrecs = []
+ for irec,rec1 in enumerate(recs1):
+  rec2 = recs2[irec]
+  assert rec1.parts[0:-1] == rec2.parts[0:-1]
+  a1 = [rec1.countstr,rec1.lsstr,rec1.ls]
+  outarr = []
+  assert ':' not in rec1.ls
+  assert ':' not in rec2.ls
+
+  # x is a 'status' field
+  if rec1.tooltip == rec2.tooltip:
+   x = '=='
+  elif rec2.tooltip.startswith(';;'):
+   x = ';;'
+   if rec1.tooltip.startswith('?'):
+    x = x + '?'
+  elif rec1.tooltip.startswith('?'):
+   #assert rec2.tooltip == rec2.tooltip
+   x = '_?'
+  else:
+   x = ''
+  a1.append(x)
+  a = ':'.join(a1)
+  # a = '%s:%s:%s' % (a,x)
+  outarr.append(a)
+  outarr.append('anna: %s' % rec2.tooltip)
+  if rec1.tooltip != rec2.tooltip:
+   outarr.append(';')
+   outarr.append('cdsl: %s' % rec1.tooltip)
+  #else:
+  # outarr.append('cdsl: %s' % 'SAME')
+  outarr.append('; ------------------------------------------------------------')
+  outrecs.append(outarr)
+ with codecs.open(fileout,"w","utf-8") as f:
+  for outarr in outrecs:
+   for out in outarr:
+    f.write(out+'\n')
+ print(len(recs1),"records written to",fileout)
+
+class Tagcount:
+ def __init__(self,line):
+  self.line = line
+  parts = line.split('\t') # tab-separated values
+  self.parts0 = parts
+  self.status =  len(parts) == 4
+  self.parts = [p.strip() for p in parts]
+  self.countstr, self.lsstr,self.ls,self.tooltip = self.parts
+  assert self.lsstr in ('ls','lsfm','lsfm?')
+
+def init_tagcount(filein):
+ lines = read_lines(filein)
+ recs = [Tagcount(line) for line in lines]
+ return recs
+
+def check1(recs):
+ recs1 = [rec for rec in recs if rec.status == False]
+ print(len(recs1),"records with wrong number of fields")
+ for irec,rec in enumerate(recs):
+  if rec.status == False:
+   print('line %s has %s parts' %(irec+1,len(rec.parts)))
+   for ipart,part in enumerate(rec.parts):
+    print('part[%s] = %s' %(ipart+1,rec.parts[ipart]))
+def check2(recs1,filein1,recs2,filein2):
+ print('%s has %s records' % (filein1,len(recs1)))
+ check1(recs1)
+ print('%s has %s records' % (filein2,len(recs2)))
+ check1(recs2)
+
+def check3(recs1,recs2):
+ n = 0
+ diffs = []
+ for irec,rec1 in enumerate(recs1):
+  rec2 = recs2[irec]
+  if ((rec1.countstr == rec2.countstr) and
+      (rec1.lsstr == rec2.lsstr) and
+      (rec1.ls == rec2.ls)):
+   pass
+  else:
+   n = n + 1
+   diff = (rec1,rec2,irec)
+   diffs.append(diff)
+   if False:
+    print('check3 difference at line %s' % (irec+1,))
+    print(rec1.line)
+    print(rec2.line)
+ print('check3 finds %s problems' %n)
+ return diffs
+
+if __name__=="__main__":
+ filein = sys.argv[1] # tagcount_ls_0.txt (cdsl)
+ filein1 = sys.argv[2] # tagcount_ls_anna_0.txt
+ fileout = sys.argv[3] # both files written to facilitate comparison
+
+ recs1 = init_tagcount(filein)
+ recs2 = init_tagcount(filein1)
+ check2(recs1,filein,recs2,filein1)
+ assert len(recs1) == len(recs2)
+ diffs_check3 = check3(recs1,recs2)
+ if diffs_check3 != []:
+  write_diffs_check3(fileout,diffs_check3)
+ else:
+  write_compare(fileout,recs1,recs2)
+