--- a/src/eric7/EricUtilities/__init__.py Thu Sep 26 09:48:49 2024 +0200
+++ b/src/eric7/EricUtilities/__init__.py Thu Sep 26 15:49:36 2024 +0200
@@ -7,8 +7,12 @@
Package containing utility modules and functions.
"""
+import codecs
+import contextlib
import os
+import re
+import chardet
import semver
from PyQt6.QtCore import QByteArray, QCoreApplication
@@ -280,3 +284,199 @@
return QCoreApplication.translate("EricUtilities", "{0} TiB").format(
loc.toString(size, "f", 2)
)
+
+
+def decodeString(text):
+ """
+ Function to decode a string containing Unicode encoded characters.
+
+ @param text text containing encoded chars
+ @type str
+ @return decoded text
+ @rtype str
+ """
+ buf = b""
+ index = 0
+ while index < len(text):
+ if text[index] == "\\":
+ qb = QByteArray.fromHex(text[index : index + 4].encode())
+ buf += bytes(qb)
+ index += 4
+ else:
+ buf += codecs.encode(text[index], "utf-8")
+ index += 1
+ buf = buf.replace(b"\x00", b"")
+ return decodeBytes(buf)
+
+
+def decodeBytes(buffer):
+ """
+ Function to decode some byte text into a string.
+
+ @param buffer byte buffer to decode
+ @type bytes
+ @return decoded text
+ @rtype str
+ """
+ # try UTF with BOM
+ with contextlib.suppress(UnicodeError, LookupError):
+ if buffer.startswith(codecs.BOM_UTF8):
+ # UTF-8 with BOM
+ return str(buffer[len(codecs.BOM_UTF8) :], encoding="utf-8")
+ elif buffer.startswith(codecs.BOM_UTF16):
+ # UTF-16 with BOM
+ return str(buffer[len(codecs.BOM_UTF16) :], encoding="utf-16")
+ elif buffer.startswith(codecs.BOM_UTF32):
+ # UTF-32 with BOM
+ return str(buffer[len(codecs.BOM_UTF32) :], encoding="utf-32")
+
+ # try UTF-8
+ with contextlib.suppress(UnicodeError):
+ return str(buffer, encoding="utf-8")
+
+ # try codec detection
+ try:
+ guess = chardet.detect(buffer)
+ if guess and guess["encoding"] is not None:
+ codec = guess["encoding"].lower()
+ return str(buffer, encoding=codec)
+ except (LookupError, UnicodeError):
+ pass
+ except ImportError:
+ pass
+
+ return str(buffer, encoding="utf-8", errors="ignore")
+
+
+def readStringFromStream(stream):
+ """
+ Module function to read a string from the given stream.
+
+ @param stream data stream opened for reading
+ @type QDataStream
+ @return string read from the stream
+ @rtype str
+ """
+ data = stream.readString()
+ if data is None:
+ data = b""
+ return data.decode("utf-8")
+
+
+###############################################################################
+## Functions for HTML string handling.
+###############################################################################
+
+
+_escape = re.compile("[&<>\"'\u0080-\uffff]")
+
+_escape_map = {
+ "&": "&",
+ "<": "<",
+ ">": ">",
+ '"': """,
+ "'": "'",
+}
+
+
+def escape_entities(m, escmap=_escape_map):
+ """
+ Function to encode html entities.
+
+ @param m the match object
+ @type re.Match
+ @param escmap the map of entities to encode
+ @type dict
+ @return the converted text
+ @rtype str
+ """
+ char = m.group()
+ text = escmap.get(char)
+ if text is None:
+ text = "&#{0:d};".format(ord(char))
+ return text
+
+
+def html_encode(text, pattern=_escape):
+ """
+ Function to correctly encode a text for html.
+
+ @param text text to be encoded
+ @type str
+ @param pattern search pattern for text to be encoded
+ @type str
+ @return the encoded text
+ @rtype str
+ """
+ if not text:
+ return ""
+ text = pattern.sub(escape_entities, text)
+ return text
+
+
+_uescape = re.compile("[\u0080-\uffff]")
+
+
+def escape_uentities(m):
+ """
+ Function to encode html entities.
+
+ @param m the match object
+ @type re.Match
+ @return the converted text
+ @rtype str
+ """
+ char = m.group()
+ text = "&#{0:d};".format(ord(char))
+ return text
+
+
+def html_uencode(text, pattern=_uescape):
+ """
+ Function to correctly encode a unicode text for html.
+
+ @param text text to be encoded
+ @type str
+ @param pattern search pattern for text to be encoded
+ @type str
+ @return the encoded text
+ @rtype str
+ """
+ if not text:
+ return ""
+ text = pattern.sub(escape_uentities, text)
+ return text
+
+
+_uunescape = re.compile(r"&#\d+;")
+
+
+def unescape_uentities(m):
+ """
+ Function to decode html entities.
+
+ @param m the match object
+ @type re.Match
+ @return the converted text
+ @rtype str
+ """
+ char = m.group()
+ ordinal = int(char[2:-1])
+ return chr(ordinal)
+
+
+def html_udecode(text, pattern=_uunescape):
+ """
+ Function to correctly decode a html text to a unicode text.
+
+ @param text text to be decoded
+ @type str
+ @param pattern search pattern for text to be decoded
+ @type str
+ @return the decoded text
+ @rtype str
+ """
+ if not text:
+ return ""
+ text = pattern.sub(unescape_uentities, text)
+ return text
