aboutsummaryrefslogtreecommitdiff
path: root/src/utils/parse/__init__.py
blob: dd13ecbcf9faea735b8febf2983fff90893329d3 (about) (plain) (blame)
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
import decimal, io, re, typing
from src.utils import datetime, errors

from .spec import *
from .time import duration
from .types import try_int
from . import sed

COMMENT_TYPES = ["#", "//"]
def hashflags(filename: str
        ) -> typing.List[typing.Tuple[str, typing.Optional[str]]]:
    hashflags = [] # type: typing.List[typing.Tuple[str, typing.Optional[str]]]
    with io.open(filename, mode="r", encoding="utf8") as f:
        for line in f:
            line = line.strip("\n")
            found = False
            for comment_type in COMMENT_TYPES:
                if line.startswith(comment_type):
                    line = line.replace(comment_type, "", 1).lstrip()
                    found = True
                    break

            if not found:
                break
            elif line.startswith("--"):
                hashflag, sep, value = line[2:].partition(" ")
                hashflags.append((hashflag, (value if sep else None)))
    return hashflags

class Docstring(object):
    def __init__(self, description: str, items: typing.Dict[str, str],
            var_items: typing.Dict[str, typing.List[str]]):
        self.description = description
        self.items = items
        self.var_items = var_items

def docstring(s: str) -> Docstring:
    description = ""
    last_item = None
    last_item_no_space = False
    items = {} # type: typing.Dict[str, str]
    var_items = {} # type: typing.Dict[str, typing.List[str]]
    if s:
        for line in s.split("\n"):
            line = line.strip()

            if line:
                if line[0] == ":":
                    key, _, value = line[1:].partition(": ")
                    last_item = key.lstrip("-")
                    last_item_no_space = key.startswith("-")

                    if key in var_items:
                        var_items[last_item].append(value)
                    elif key in items:
                        var_items[last_item] = [items.pop(last_item), value]
                    else:
                        items[last_item] = value
                else:
                    if last_item:
                        if last_item_no_space:
                            items[last_item] += line
                        else:
                            items[last_item] += " %s" % line
                    else:
                        if description:
                            description += " "
                        description += line
    return Docstring(description, items, var_items)

def keyvalue(s: str, delimiter: str=" "
        ) -> typing.Dict[str, typing.Optional[str]]:
    items = {} # type: typing.Dict[str, typing.Optional[str]]
    pairs = s.split(delimiter)
    for pair in filter(None, pairs):
        key, sep, value = pair.partition("=")
        if sep:
            items[key] = value
        else:
            items[key] = None
    return items

def line_normalise(s: str) -> str:
    lines = list(filter(None, [line.strip() for line in s.split("\n")]))
    return "  ".join(line.replace("  ", " ") for line in lines)

def parse_number(s: str) -> str:
    try:
        decimal.Decimal(s)
        return s
    except:
        pass

    unit = s[-1].lower()
    number_str = s[:-1]
    try:
        number = decimal.Decimal(number_str)
    except:
        raise ValueError("Invalid format '%s' passed to parse_number" %
            number_str)

    if unit == "k":
        number *= decimal.Decimal("1_000")
    elif unit == "m":
        number *= decimal.Decimal("1_000_000")
    elif unit == "b":
        number *= decimal.Decimal("1_000_000_000")
    else:
        raise ValueError("Unknown unit '%s' given to parse_number" % unit)
    return str(number)

def format_tokens(s: str, names: typing.List[str], sigil: str="$"
        ) -> typing.List[typing.Tuple[int, str]]:
    names = names.copy()
    names.sort()
    names.reverse()

    i = 0
    max = len(s)-1
    sigil_found = False
    tokens: typing.List[typing.Tuple[int, str]] = []

    while i < max:
        if s[i] == sigil:
            i += 1
            if not s[i] == sigil:
                for name in names:
                    if len(name) <= (len(s)-i) and s[i:i+len(name)] == name:
                        tokens.append((i-1, "%s%s" % (sigil, name)))
                        i += len(name)
                        break
            else:
                tokens.append((i-1, "$$"))
        i += 1
    return tokens

def format_token_replace(s: str, vars: typing.Dict[str, str],
        sigil: str="$") -> str:
    vars = vars.copy()
    vars.update({sigil: sigil})
    tokens = format_tokens(s, list(vars.keys()), sigil)
    tokens.sort(key=lambda x: x[0])
    tokens.reverse()
    for i, token in tokens:
        s = s[:i] + vars[token.replace(sigil, "", 1)] + s[i+len(token):]
    return s