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
|
class VariableRestrictionRage:
def __init__(self, min, max):
self.min = min
self.max = max
def __str__(self):
return f"Range({self.min}-{self.max})"
class VariableRestrictionGreaterThen:
def __init__(self, value):
self.value = value
def __str__(self):
return f"Greater({self.value})"
class VariableRestrictionLessThen:
def __init__(self, value):
self.value = value
def __str__(self):
return f"Less({self.value})"
class VariableRestrictionEqualTo:
def __init__(self, value):
self.value = value
def __str__(self):
return f"Equal({self.value})"
class VariableDescription():
def __init__(self, name):
self.name = name
self.description = ""
self.shallBe = None
def __str__(self):
if (self.shallBe):
return f"{self.name} -- {self.shallBe}"
else:
return f"{self.name}"
def finishReading(self):
self.cleanDescriptionText()
self.lookForShallBe()
def cleanDescriptionText(self):
self.description = self.description.replace(u'\xa0', u' ')
def lookForShallBe(self):
searchStrings = []
searchStrings.append(self.name + " shall be ")
searchStrings.append("the value of " + self.name + " shall be ")
for searchString in searchStrings:
posShallBe = self.description.lower().find(searchString)
if (posShallBe != -1):
posDot = self.description.find(".", posShallBe)
if (posDot != -1):
self.parseRestriction(
self.description[posShallBe + len(searchString): posDot])
return
def parseRestriction(self, restrictionText):
conditionList = ["in the range of ", "greater than ",
"greater then ", "less than ", "less then ", "equal to "]
for idx, condition in enumerate(conditionList):
conditionPos = restrictionText.find(condition)
conditionStart = conditionPos + len(condition)
if (conditionPos != -1):
conditionIndex = idx
break
if (conditionPos == -1):
ignoreCases = ["the same for all pictures ",
"the same in all ",
"the same for all PPSs "]
for c in ignoreCases:
if (c in restrictionText):
return
if (restrictionText == "0"):
print("Warning: Restriction just says 'shall be 0'.")
self.shallBe = VariableRestrictionEqualTo("0")
return
print("TODO: Add this restriction: " + restrictionText)
return
if (conditionIndex == 0):
posMinEnd = restrictionText.find(" to ", conditionStart)
posMaxStart = posMinEnd + len(" to ")
posMaxEnd = restrictionText.find(", inclusive", posMaxStart)
if (posMinEnd == -1 or posMaxStart == -1 or posMaxEnd == -1):
print("Error parsing range")
return
self.shallBe = VariableRestrictionRage(
restrictionText[conditionStart: posMinEnd], restrictionText[posMaxStart: posMaxEnd])
elif (conditionIndex in [1, 2]):
self.shallBe = VariableRestrictionGreaterThen(
restrictionText[conditionStart:])
elif (conditionIndex in [3, 4]):
self.shallBe = VariableRestrictionLessThen(
restrictionText[conditionStart:])
elif (conditionIndex == 5):
self.shallBe = VariableRestrictionEqualTo(
restrictionText[conditionStart:])
else:
assert(False)
if (conditionIndex in [2, 4]):
print("Warning: Using then in a comparison.")
def parseDocForVariableDescriptions(document):
firstLastEntry = ["NAL unit header semantics", "Slice data semantics"]
firstEntryFound = False
variableDescriptions = dict()
currentDescription = None
for paragraph in document.paragraphs:
if (firstLastEntry[0] in paragraph.text):
firstEntryFound = True
if (firstLastEntry[1] in paragraph.text):
break
if (firstEntryFound):
if (len(paragraph.runs) > 1):
runText = paragraph.runs[0].text
isBold = paragraph.runs[0].font.bold
if (isBold):
if (currentDescription != None):
currentDescription.finishReading()
variableDescriptions[currentDescription.name] = currentDescription
# It can happen that the variable description is split over multiple
# runs. It will all be bold without spaces and can just be concatenated.
# Please don't ask me why.
runIndex = 1
for i in range(1, len(paragraph.runs)):
isBold = paragraph.runs[i].font.bold
text = paragraph.runs[i].text
containsSpaceAtEnd = (text[-1] == " ")
if (containsSpaceAtEnd):
text = text[:-1]
containesSpaces = (text.find(" ") != -1)
if (isBold and not containesSpaces):
runText += text
else:
break
if (containsSpaceAtEnd):
break
runIndex += 1
currentDescription = VariableDescription(runText)
# Get all the text after the variable name
for i in range(runIndex, len(paragraph.runs)):
runText = paragraph.runs[i].text
currentDescription.description += runText
continue
if (currentDescription != None):
currentDescription.description += paragraph.text
if (currentDescription != None):
currentDescription.finishReading()
variableDescriptions[currentDescription.name] = currentDescription
return variableDescriptions
|
