Compare commits

...

9 Commits

Author SHA1 Message Date
Clemens Schwaighofer
2fa031f6ee Comment out log handlers until we rebuild the logging class 2025-07-08 10:01:09 +09:00
Clemens Schwaighofer
f38cce1c1d Rename src CoreLibs to corelibs 2025-07-08 09:58:33 +09:00
Clemens Schwaighofer
52dd1e7b73 Fix base folder name, must be lower case 2025-07-08 09:56:43 +09:00
Clemens Schwaighofer
661a182655 Fix __init__.py 2025-07-08 09:47:55 +09:00
Clemens Schwaighofer
d803de312d Change log file formatter order 2025-07-08 09:46:00 +09:00
Clemens Schwaighofer
57a36d64f1 UV install information link 2025-07-04 10:55:10 +09:00
Clemens Schwaighofer
0cc4883fa1 Move the mask from string to dict helpers, add end comment 2025-07-03 14:01:40 +09:00
Clemens Schwaighofer
1eb464dd2c Add string handling helper maks to mask strings 2025-07-03 13:57:39 +09:00
Clemens Schwaighofer
f900a6eab9 Add double byte string format 2025-07-02 18:34:53 +09:00
38 changed files with 362 additions and 9 deletions

View File

@@ -20,7 +20,11 @@ This is a pip package that can be installed into any project and covers the foll
- logging_handling: extend log and also error message handling
- requests_handling: requests wrapper for better calls with auth headers
- script_handling: pid lock file handling, abort timer
- string_handling: byte format, datetime format, hashing, string formats for numbrers, etc
- string_handling: byte format, datetime format, hashing, string formats for numbrers, double byte string format, etc
## UV setup
uv must be [installed](https://docs.astral.sh/uv/getting-started/installation/)
## How to publish
@@ -41,7 +45,7 @@ uv publish --index egra-gitea --token <gitea token> --native-tls
## Test package
We must set the full index URL here because we run with "--no-project2
We must set the full index URL here because we run with "--no-project"
```sh
uv run --with corelibs --index egra-gitea=https://git.egplusww.jp/api/packages/PyPI/pypi/simple/ --no-project --native-tls -- python -c "import corelibs"
@@ -51,12 +55,16 @@ uv run --with corelibs --index egra-gitea=https://git.egplusww.jp/api/packages/P
In the test folder other tests are located.
At the moment only a small test for the "progress" module is set
At the moment only a small test for the "progress" and the "double byte string format" module is set
```sh
uv run --native-tls tests/progress/progress_test.py
```
```sh
uv run --native-tls tests/double_byte_string_format/double_byte_string_format.py
```
## How to install in another project
This will also add the index entry

View File

@@ -1,7 +1,7 @@
# MARK: Project info
[project]
name = "corelibs"
version = "0.3.1"
version = "0.5.0"
description = "Collection of utils for Python scripts"
readme = "ReadMe.md"
requires-python = ">=3.13"

View File

@@ -89,3 +89,5 @@ class CsvWriter:
csv_row[value] = line[key]
self.csv_file_writer.writerow(csv_row)
return True
# __END__

View File

@@ -110,5 +110,4 @@ class Timer:
"""
return self._run_time
# __END__

View File

@@ -42,3 +42,5 @@ def file_name_crc(file_path: Path, add_parent_folder: bool = False) -> str:
return str(Path(file_path.parent.name).joinpath(file_path.name))
else:
return file_path.name
# __END__

View File

@@ -126,3 +126,5 @@ def value_lookup(haystack: dict[str, str], value: str, raise_on_many: bool = Fal
if raise_on_many is True and len(keys) > 1:
raise ValueError("More than one element found with the same name")
return keys[0]
# __END__

View File

@@ -0,0 +1,37 @@
"""
Dict helpers
"""
def mask(
data_set: dict[str, str],
mask_keys: list[str] | None = None,
mask_str: str = "***",
skip: bool = False
) -> dict[str, str]:
"""
mask data for output
Checks if mask_keys list exist in any key in the data set either from the start or at the end
Arguments:
data_set {dict[str, str]} -- _description_
Keyword Arguments:
mask_keys {list[str] | None} -- _description_ (default: {None})
mask_str {str} -- _description_ (default: {"***"})
skip {bool} -- _description_ (default: {False})
Returns:
dict[str, str] -- _description_
"""
if skip is True:
return data_set
if mask_keys is None:
mask_keys = ["password", "secret"]
return {
key: mask_str
if any(key.startswith(mask_key) or key.endswith(mask_key) for mask_key in mask_keys) else value
for key, value in data_set.items()
}
# __END__

View File

@@ -35,3 +35,5 @@ def dict_hash_crc(data: dict[Any, Any] | list[Any]) -> str:
return hashlib.sha256(
json.dumps(data, sort_keys=True, ensure_ascii=True).encode('utf-8')
).hexdigest()
# __END__

View File

@@ -59,3 +59,5 @@ def build_dict(
dict[str, Any | list[Any] | dict[Any, Any]],
delete_keys_from_set(any_dict, ignore_entries)
)
# __END__

View File

@@ -30,6 +30,8 @@ class Log:
self.logger = logging.getLogger(log_name)
# set maximum logging level for all logging output
self.logger.setLevel(logging.DEBUG)
# self.handlers = []
# console logger
self.__console_handler(log_level_console)
# file logger
@@ -74,8 +76,8 @@ class Log:
formatter_file_handler = logging.Formatter(
(
'[%(asctime)s.%(msecs)03d] '
'[%(pathname)s:%(funcName)s:%(lineno)d] '
'[%(name)s:%(process)d] '
'[%(pathname)s:%(funcName)s:%(lineno)d] '
'<%(levelname)s> '
'%(message)s'
),

View File

@@ -93,3 +93,5 @@ def unlock_run(lock_file: Path) -> None:
lock_file.unlink()
except IOError as e:
raise IOError(f"Cannot remove lock_file: {lock_file}: {e}") from e
# __END__

View File

@@ -60,5 +60,4 @@ def create_time(timestamp: float, timestamp_format: str = "%Y-%m-%d %H:%M:%S") -
"""
return time.strftime(timestamp_format, time.localtime(timestamp))
# __END__

View File

@@ -0,0 +1,226 @@
"""
Format double byte strings to exact length
"""
import unicodedata
class DoubleByteFormatString:
"""
Format a string to exact length
"""
def __init__(
self,
string: str,
cut_length: int,
format_length: int | None = None,
placeholder: str = '..',
format_string: str = '{{:<{len}}}'
):
"""
shorts a string to exact cut length and sets it to format length
after "cut_length" cut the "placeholder" will be added, so that the new cut_length is never
larget than the cut_length given (".." is counted to cut_length)
if format_length if set and outside format_length will be set
the cut_length is adjusted to format_length if the format_length is shorter
Example
"Foo bar baz" 10 charcters -> 5 cut_length -> 10 format_length
"Foo.. "
use class.get_string_short() for cut length shortend string
use class.get_string_short_formated() to get the shorted string to format length padding
creates a class that shortens and sets the format length
to use with a print format run the format needs to be pre set in
the style of {{:<{len}}} style
self.get_string_short_formated() for the "len" parameter
Args:
string (str): string to work with
cut_length (int): width to shorten to
format_length (int | None): format length. Defaults to None
placeholder (str, optional): placeholder to put after shortened string. Defaults to '..'.
format_string (str, optional): format string. Defaults to '{{:<{len}}}'
"""
# output variables
self.string_short: str = ''
self.string_width_value: int = 0
self.string_short_width: int = 0
self.format_length_value: int = 0
# internal varaibles
self.placeholder: str = placeholder
# original string
self.string: str = ''
# width to cut string to
self.cut_length: int = 0
# format length to set to
self.format_length: int = 0
# main string
self.string = str(string)
self.format_string: str = format_string
# if width is > 0 set, else set width of string (fallback)
if cut_length > 0:
self.cut_length = cut_length
elif cut_length <= 0:
self.cut_length = self.__string_width_calc(self.string)
# format length set, if not set or smaller than 0, set to width of string
self.format_length = self.cut_length
if format_length is not None and format_length > 0:
self.format_length = format_length
# check that width is not larger then length if yes, set width to length
self.cut_length = min(self.cut_length, self.format_length)
# process the string shorten and format length calculation
self.process()
def process(self):
"""
runs all the class methods to set string length, the string shortened
and the format length
"""
# call the internal ones to set the data
if self.string:
self.__string_width()
self.__shorten_string()
if self.format_length:
self.__format_length()
def get_string_short(self) -> str:
"""
get the shortend string
Returns:
str -- _description_
"""
return self.string_short
def get_string_short_formated(self, format_string: str = '{{:<{len}}}') -> str:
"""
get the formatted string
Keyword Arguments:
format_string {_type_} -- _description_ (default: {'{{:<{len}}}'})
Returns:
str -- _description_
"""
if not format_string:
format_string = self.format_string
return format_string.format(
len=self.get_format_length()
).format(
self.get_string_short()
)
def get_format_length(self) -> int:
"""
get the format length for outside length set
Returns:
int -- _description_
"""
return self.format_length_value
def get_cut_length(self) -> int:
"""
get the actual cut length
Returns:
int -- _description_
"""
return self.cut_length
def get_requested_cut_length(self) -> int:
"""
get the requested cut length
Returns:
int -- _description_
"""
return self.cut_length
def get_requested_format_length(self) -> int:
"""
get the requested format length
Returns:
int -- _description_
"""
return self.format_length
def __string_width_calc(self, string: str) -> int:
"""
does the actual string width calculation
Args:
string (str): string to calculate from
Returns:
int: stringth width
"""
return sum(1 + (unicodedata.east_asian_width(c) in "WF") for c in string)
def __string_width(self):
"""
calculates the string width based on the characters
this is an internal method and should not be called on itself
"""
# only run if string is set and is valid string
if self.string:
# calculate width. add +1 for each double byte character
self.string_width_value = self.__string_width_calc(self.string)
def __format_length(self):
"""
set the format length based on the length for the format
and the shortend string
this is an internal method and should not be called on itself
"""
if not self.string_short:
self.__shorten_string()
# get correct format length based on string
if (
self.string_short and
self.format_length > 0 and
self.string_short_width > 0
):
# length: format length wanted
# substract the width of the shortend string - the length of the shortend string
self.format_length_value = self.format_length - (self.string_short_width - len(self.string_short))
else:
# if we have nothing to shorten the length, keep the old one
self.format_length_value = self.format_length
def __shorten_string(self):
"""
shorten string down to set width
this is an internal method and should not be called on itself
"""
# set string width if not set
if not self.string_width_value:
self.__string_width()
# if the double byte string width is larger than the wanted width
if self.string_width_value > self.cut_length:
cur_len = 0
self.string_short = ''
for char in str(self.string):
# set the current length if we add the character
cur_len += 2 if unicodedata.east_asian_width(char) in "WF" else 1
# if the new length is smaller than the output length to shorten too add the char
if cur_len <= (self.cut_length - len(self.placeholder)):
self.string_short += char
self.string_short_width = cur_len
# return string with new width and placeholder
self.string_short = f"{self.string_short}{self.placeholder}"
self.string_short_width += len(self.placeholder)
else:
# if string is same saze just copy
self.string_short = self.string
# __END__

View File

@@ -36,3 +36,5 @@ def sha1_short(string: str) -> str:
str -- _description_
"""
return hashlib.sha1(string.encode('utf-8')).hexdigest()[:9]
# __END__

View File

@@ -0,0 +1,66 @@
#!/usr/bin/env -S uv run --script
"""
Test for double byte format
"""
from corelibs.string_handling.double_byte_string_format import DoubleByteFormatString
def main():
"""
Main call
"""
string = [
"Some string 123 other text",
"Some string 日本語 other text",
"日本語は string 123 other text",
"あいうえおかきくけこさしすせそなにぬねのまみむめも〜",
"あいうえおかきくけこさしす 1 other text",
"Some string すせそなにぬねのまみむめも〜",
"SOME OTHER STRING THAT IS LONGER THAN TWENTYSIX CHARACTERS",
"日本語は string 123 other text Some string 日本語 other text"
]
format_str = "{{:<{len}}}"
length_set = [
(26, 25),
(26, 26),
(26, 60),
(26, 20),
(26, -5),
(-6, -5),
]
for _length_set in length_set:
cut_length = _length_set[0]
format_length = _length_set[1]
print(f"========= Cut: {cut_length} | Format: {format_length} ==> ")
for _string in string:
string_test = DoubleByteFormatString(_string, cut_length, format_length)
formated = format_str.format(
len=string_test.get_format_length()
).format(
string_test.get_string_short()
)
print(
"* Shorten string: shorten length: "
f"Req: {string_test.get_requested_cut_length()} ({cut_length}) / "
f"Set: {string_test.get_cut_length()}, "
"format length: "
f"Req: {string_test.get_requested_format_length()} ({format_length}) / "
f"Set: {string_test.get_format_length()}"
f"\nOrig: |{_string}|"
f"\nGSS : |{string_test.get_string_short()}|"
f"\nF : |{formated}|"
f"\nGSSF: |{string_test.get_string_short_formated()}|"
)
print("-------")
if __name__ == "__main__":
main()
# __END__

View File

@@ -1,4 +1,4 @@
#!/usr/bin/env python3
#!/usr/bin/env -S uv run --script
"""
Test for progress class
@@ -89,3 +89,5 @@ def main():
if __name__ == '__main__':
main()
# __END__

2
uv.lock generated
View File

@@ -35,7 +35,7 @@ wheels = [
[[package]]
name = "corelibs"
version = "0.3.0"
version = "0.4.0"
source = { editable = "." }
dependencies = [
{ name = "jmespath" },