summaryrefslogtreecommitdiffstats
path: root/parsers/survex.py
blob: 540ea0bd1749ed5d93e34d76e4fdf202a0e48ecb (plain)
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
import settings
import expo.models as models
import re
import os

roles = {"Insts": "Insts",
         "insts": "Insts",
         "Instruments": "Insts",
         "instruments": "Insts",
         "Inst": "Insts",
         "inst": "Insts",
         "dog": "Other",
         "Dog": "Other",
         "other": "Other",
         "Other": "Other",
         "Notes": "Notes",
         "notes": "notes",
         "pics": "Pics",
         "Pics": "Pics",
         "Tape": "Tape",
         "tape": "Tape"}

re_include_extension = re.compile(r"^\s*\*include\s+([^\s]*).svx$", re.IGNORECASE)
re_include_no_extension = re.compile(r"^\s*\*include\s+([^\s]*)$", re.IGNORECASE)
flags = {"begin": re.compile(r"^\s*\*begin\s+(.*?)\s*$", re.IGNORECASE),
         "end": re.compile(r"^\s*\*end\s+(.*?)\s*$", re.IGNORECASE),
         "date": re.compile(r"^\s*\*date\s+(.*?)\s*$", re.IGNORECASE),
         "team": re.compile(r"^\s*\*team\s+(.*?)\s*$", re.IGNORECASE)}

def fileIterator(directory, filename):
    survex_file = os.path.join(directory, filename + ".svx")
    try:
        f = open(os.path.join(settings.SURVEX_DATA, survex_file), "rb")
    except:
        f = open(os.path.join(settings.SURVEX_DATA, survex_file).lower(), "rb")
    char = 0
    for line in f.readlines():
        line = unicode(line, "latin1")
        include_extension = re_include_extension.match(line)
        include_no_extension = re_include_no_extension.match(line)
        def a(include):
            link = re.split(r"/|\\", include)
            return fileIterator(os.path.join(directory, *link[:-1]), link[-1])
        if include_extension:
            for sf, c, l in a(include_extension.groups()[0]):
                yield sf, c, l
        elif include_no_extension:
            for sf, c, l in a(include_no_extension.groups()[0]):
                yield sf, c, l
        else:
            yield survex_file, char, line
        char = char + len(line)

def make_model(name, parent, iter_lines, sf, c, l):
    if parent:
        m = models.SurvexBlock(name = name, parent = parent, begin_file = sf, begin_char = c, text = l)
    else:
        m = models.SurvexBlock(name = name, begin_file = sf, begin_char = c, text = l)
    m.save()

    def saveEnd(survex_file, count):
          if m.start_year and team:
              try:
                  exp = models.Expedition.objects.get(year = str(file_year[1]))
                  for file_, (role, names) in team:
                      if names.strip("\t").strip(" ") == "both" or names.strip("\t").strip(" ") == "Both":
                          names = reduce(lambda x, y: x + u" & " + y,
                                         [names for file_, (role, names) in team
                                                if names.strip("\t").strip(" ") != "both"
                                                   and names.strip("\t").strip(" ") != "Both"])
                      for name in re.split("&|/|\+|,|;", names):
                          try:
                              models.PersonRole(person = exp.GetPersonExpedition(name.strip(" ")).person,
                                                survex_block = m,
                                                role = models.Role.objects.get(name = roles[role])).save()
                          except AttributeError:
                              print "Person not found: " + name + " in " + file_
              except AssertionError, inst:
                  print inst, ": ", file_year[0]

          m.end_file = survex_file
          m.end_char = count
          m.save()
    team = []
    file_year = None
    for survex_file, count, line in iter_lines:
      #Dictionary compreshension
      res = dict([(key, regex.match(line.split(";")[0])) for key, regex in flags.iteritems()])
      if res["begin"]:
          make_model(res["begin"].groups()[0], m, iter_lines, survex_file, count, line)
      else:
          m.text = m.text + line
      if res["end"]:
          saveEnd(survex_file, count)
          assert (res["end"].groups()[0]).lower() == (name).lower()
          return None
      elif res["date"]:
          datere = re.match("(\d+)(?:\.(\d+))?(?:\.(\d+))?(?:-(\d+))?(?:\.(\d+))?(?:\.(\d+))?",
                            res["date"].groups()[0])
          if datere is not None:
              startYear, startMonth, startDay, endYear, endMonth, endDay = datere.groups()
              m.start_year = startYear
              m.start_month = startMonth
              m.start_day = startDay
              m.end_year = endYear
              m.end_month = endMonth
              m.end_day = endDay
          file_year = survex_file, startYear
      elif res["team"]:
          h = re.match("((?:[Ii]nst(?:s|ruments)?)|(?:[Pp]ics)|(?:[Tt]ape)|(?:[Nn]otes)|(?:[Oo]ther))\s*(.*)",
                       res["team"].groups()[0])
          if h:
              team.append((survex_file, h.groups()))
          else:
              print "Role not found: " +  line + " in: " + sf
    m.text = m.text + line
    saveEnd(survex_file, count)


for role in ["Insts", "Notes", "Pics", "Tape", "Other"]:
    models.Role(name = role).save()

filename = "all"
make_model("", None, fileIterator("", filename), filename, 0, "")