FilesExpand file tree

 main

/

temp_helpers.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

156 lines (128 loc) · 4.83 KB

 main

/

temp_helpers.py

Copy path

Top

File metadata and controls

• Code
• Blame

156 lines (128 loc) · 4.83 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

import openpyxl

from openpyxl.cell.cell import Cell

import re

# Regex for email validation

EMAIL_REGEX = re.compile(r"^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+$")

def infer_cell_data_type(cell: openpyxl.cell.cell.Cell) -> str:

"""

Infers the data type of a cell based on its openpyxl data_type and value.

"""

if cell.value is None:

return "empty"

# Check for email format using regex on the string value first

if isinstance(cell.value, str) and EMAIL_REGEX.match(cell.value):

return "email"

data_type = cell.data_type

if data_type == 's':

return "text"

elif data_type == 'n':

return "numeric"

elif data_type == 'b':

return "boolean"

elif data_type == 'd':

return "datetime"

elif data_type == 'e':

return "error"

elif data_type == 'f':

if cell.value is not None:

if isinstance(cell.value, str):

return "text"

elif isinstance(cell.value, (int, float)):

return "numeric"

elif isinstance(cell.value, bool):

return "boolean"

else:

return "formula_cached_value"

return "formula"

elif data_type == 'g':

if cell.value is not None:

return "text"

else:

return "empty"

else:

return "unknown"

def categorize_number_format(number_format_string: str, cell: Cell) -> str:

"""

Categorizes the number format of a cell, using the cell itself for context.

"""

cell_data_type = infer_cell_data_type(cell)

if cell_data_type not in ["numeric", "datetime"]:

return "not_applicable"

if number_format_string is None or number_format_string.lower() == "general":

if cell_data_type == "datetime":

return "datetime_general"

return "general"

if number_format_string == "@" or number_format_string.lower() == "text":

return "text_format"

if any(c in number_format_string for c in ['$', '€', '£', '¥']):

return "currency"

if '%' in number_format_string:

return "percentage"

if 'E+' in number_format_string or 'E-' in number_format_string.upper():

return "scientific"

if '#' in number_format_string and '/' in number_format_string and '?' in number_format_string:

return "fraction"

is_date_format = False

is_time_format = False

nf_lower = number_format_string.lower()

date_keywords = ['yyyy', 'yy', 'mmmm', 'mmm', 'mm', 'dddd', 'ddd', 'dd', 'd']

if any(keyword in nf_lower for keyword in date_keywords):

is_date_format = True

time_keywords = ['hh', 'h', 'ss', 's', 'am/pm', 'a/p']

if any(keyword in nf_lower for keyword in time_keywords):

is_time_format = True

if ':' in number_format_string:

temp_nf = number_format_string.replace('0', '').replace('#', '').replace(',', '').replace('.', '')

if ':' in temp_nf:

is_time_format = True

if is_date_format and is_time_format:

return "datetime_custom"

elif is_date_format:

return "date_custom"

elif is_time_format:

return "time_custom"

if cell_data_type == "numeric":

if number_format_string in ["0", "#,##0"]:

return "integer"

if number_format_string in ["0.00", "#,##0.00", "0.0", "#,##0.0"]:

return "float"

return "other_numeric"

if cell_data_type == "datetime":

return "other_date"

return "unknown_format_category"

def get_number_format_string(cell: Cell) -> str:

"""Return the raw number format string for a cell."""

try:

nfs = cell.number_format

if nfs is None or nfs == "":

return "General"

return str(nfs)

except Exception:

return "General"

def detect_semantic_type(cell: Cell) -> str:

"""Infer a higher level semantic type using number format and cell value."""

data_type = infer_cell_data_type(cell)

if data_type == "email":

return "email"

nfs = get_number_format_string(cell)

category = categorize_number_format(nfs, cell)

nfs_lower = nfs.lower()

if category == "percentage":

return "percentage"

if category == "currency":

return "currency"

if category in ["date_custom", "datetime_custom", "datetime_general", "other_date"]:

if ("yyyy" in nfs_lower or "yy" in nfs_lower) and not any(x in nfs_lower for x in ["m", "d"]):

return "year"

return "date"

if category == "time_custom":

return "time"

if category == "scientific":

return "scientific_notation"

if data_type == "numeric":

if isinstance(cell.value, int) or category == "integer":

return "integer"

if isinstance(cell.value, float) or category == "float":

return "float"

return "numeric" # Fallback

return data_type