Diff for "Anime"

   1 runlen_han   = counts[0]/runs[0]
   2 runlen_hira  = counts[1]/runs[1]
   3 runlen_kata  = counts[2]/runs[2]
   4 
   5 avg_counts = sum(counts[:3])/3
   6 prop_han   = counts[0]/avg_counts
   7 prop_hira  = counts[1]/avg_counts
   8 prop_kata  = counts[2]/avg_counts
   9 
  10 avg_runs = sum(runs[:3])/3
  11 prop_runs_han   = runs[0]/avg_runs
  12 prop_runs_hira  = runs[1]/avg_runs
  13 prop_runs_kata  = runs[2]/avg_runs
  14 
  15 # ....
  16 
  17 properties = [
  18     runlen_han,
  19     runlen_hira,
  20     runlen_kata,
  21     
  22     math.log(prop_han),
  23     math.log(prop_hira),
  24     math.log(prop_kata),
  25     
  26     math.log(prop_runs_han),
  27     math.log(prop_runs_hira),
  28     math.log(prop_runs_kata),
  29 ]
  30 weights = [
  31  1.6192223 ,
  32 -0.59284526,
  33 -0.16966693,
  34 -2.30292   ,
  35  0.63782173,
  36  0.62009275,
  37  1.2680697 ,
  38 -3.2421117 ,
  39 -0.8129924 ,
  40  0.01331723 # constant term
  41 ]
  42 nothayashi = weights[-1] + sum(properties[i]*weights[i] for i in range(len(properties)))
  43 nothayashi = (1-nothayashi)*50+50

   1 #!python
   2 
   3 import sys
   4 import re
   5 
   6 
   7 def print_safe(string, end="\n"):
   8     sys.stdout.buffer.write((str(string)+end).encode("utf-8"))
   9 
  10 nullify = [
  11 "[ﾃﾚﾋﾞ]",
  12 "[ｽﾋﾟｰｶ]",
  13 r"\n",
  14 r"\N",
  15 "\r",
  16 ]
  17 
  18 for arg in sys.argv[1:]:
  19     with open(arg, "r", encoding="utf-8-sig") as f:
  20         groups = f.read().split("\n\n")
  21         
  22         last_group = ""
  23         
  24         for i in range(len(groups)):
  25             groups[i] = groups[i].split("\n")[2:]
  26             
  27             if "\n".join(groups[i]) == last_group:
  28                 continue
  29             last_group = "\n".join(groups[i]) 
  30             
  31             did_print = False
  32             for j in range(len(groups[i])):
  33                 line = groups[i][j]
  34                 line = re.sub("（[^）]*）","",line)
  35                 line = re.sub(r"\([^\)]*\)","",line)
  36                 line = line.replace("《","«")
  37                 line = line.replace("》","»")
  38                 for null in nullify:
  39                     line = line.replace(null,"")
  40                 line = line.strip()
  41                 if line != "":
  42                     #print_safe(line)
  43                     did_print = True
  44             if did_print:
  45                 #print_safe("")
  46                 pass
  47         #print_safe("")
  48         print_safe(arg)

   1 #!python
   2 
   3 import sys
   4 import re
   5 
   6 def print_safe(string, end="\n"):
   7     sys.stdout.buffer.write((str(string)+end).encode("utf-8"))
   8 
   9 def parsecsv(string):
  10     fields = []
  11     insomething = False
  12 
  13 nullify = [
  14 "[ﾃﾚﾋﾞ]",
  15 "[ｽﾋﾟｰｶ]",
  16 r"\n",
  17 r"\N",
  18 ]
  19 
  20 for arg in sys.argv[1:]:
  21     with open(arg, "r", encoding="utf-8") as f:
  22         events = False
  23         last_group = ""
  24         for line in f:
  25             line = line.strip("\n")
  26             if events:
  27                 if line.startswith("Dialogue:"):
  28                     line = line.replace("Dialogue:","",1)
  29                     
  30                     # do not use the CSV parser for this
  31                     fields = line.split(",",9)
  32                     
  33                     if "人类_声明" in fields[:-1]:
  34                         continue
  35                     if "标题" in fields[:-1]:
  36                         continue
  37                     if "staff" in fields[:-1]:
  38                         continue
  39                     if "Opening" in fields[:-1]:
  40                         continue
  41                     if "Ending" in fields[:-1]:
  42                         continue
  43                     
  44                     
  45                     line = fields[-1]
  46                     basic_line = line
  47                     
  48                     # it contains drawing instructions, which we need a parser to correctly isolate and remove
  49                     # line is probably just pure drawing instructions so get rid of it
  50                     if r"\p" in line:
  51                         continue
  52                     
  53                     line = re.sub(r"\{[^\}]*\}","",line)
  54                     line = re.sub("（[^）]*）","",line)
  55                     line = re.sub(r"\([^\)]*\)","",line)
  56                     line = line.strip()
  57                     line = line.replace("《","«")
  58                     line = line.replace("》","»")
  59                     for null in nullify:
  60                         line = line.replace(null,"")
  61                     # probably per-character karaoke or something
  62                     if len(line) <= 1 and "pos" in basic_line:
  63                         continue
  64                     if line != "":
  65                         if last_group == line:
  66                             continue
  67                         last_group = line
  68                         print_safe(line)
  69             
  70             if line == "[Events]":
  71                 events = True