toolbox-utils 5.0.8__py3-none-any.whl

toolbox_utils/tssplit/setup.py

@@ -0,0 +1,38 @@
+from setuptools import setup
+
+with open("README.md", "r") as fh:
+    long_description = fh.read()
+
+setup(
+    name="tssplit",
+    version="1.0.6",
+    py_modules=["tssplit.tssplit"],
+    url="https://github.com/mezantrop/tssplit",
+    license="bsd-2-clause",
+    author="Mikhail Zakharov",
+    author_email="zmey20000@yahoo.com",
+    description="Trivial split for strings with quotes and escaped characters",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    classifiers=[
+        "License :: OSI Approved :: BSD License",
+        "Development Status :: 5 - Production/Stable",
+        "Intended Audience :: Developers",
+        "Operating System :: OS Independent",
+        "Programming Language :: Python :: 3",
+        "Topic :: Software Development",
+        "Topic :: Text Processing",
+        "Topic :: Text Processing :: Filters",
+        "Topic :: Text Processing :: General",
+    ],
+    keywords=[
+        "split",
+        "parse",
+        "quote",
+        "trim",
+        "strip",
+        "string",
+        "delimiter",
+        "separator",
+    ],
+)

toolbox_utils/tssplit/tssplit/__init__.py

@@ -0,0 +1 @@
+from .tssplit import tssplit

toolbox_utils/tssplit/tssplit/tssplit.py

@@ -0,0 +1,45 @@
+def tssplit(
+    s, quote="\"'", quote_keep=False, delimiter=":;,", escape="/^", trim="", remark="#"
+):
+    """Split a string by delimiters with quotes and escaped characters, optionally trimming results
+
+    :param s: A string to split into chunks
+    :param quote: Quote chars to protect a part of s from parsing
+    :param quote_keep: Preserve quote characters in the output or not
+    :param delimiter: A chunk separator character
+    :param escape: An escape character
+    :param trim: Trim characters from chunks
+    :param remark: Ignore all characters after remark sign
+    :return: A list of chunks
+    """
+
+    in_quotes = in_escape = False
+    token = ""
+    result = []
+
+    for c in s:
+        if in_escape:
+            token += c
+            in_escape = False
+        elif c in escape:
+            in_escape = True
+            if in_quotes:
+                token += c
+        elif c in quote:
+            in_quotes = not in_quotes
+            if quote_keep:
+                token += c
+        elif c in delimiter and not in_quotes:
+            if trim:
+                token = token.strip(trim)
+            result.append(token)
+            token = ""
+        elif c in remark:
+            break
+        else:
+            token += c
+
+    if trim:
+        token = token.strip(trim)
+    result.append(token)
+    return result