TSVZ 3.23__tar.gz → 3.25__tar.gz

{tsvz-3.23 → tsvz-3.25}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: TSVZ
-Version: 3.23
+Version: 3.25
 Summary: An simple in memory wrapper around a TSV file to function as a database
 Home-page: https://github.com/yufei-pan/TSVZ
 Author: Yufei Pan

{tsvz-3.23 → tsvz-3.25}/TSVZ.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: TSVZ
-Version: 3.23
+Version: 3.25
 Summary: An simple in memory wrapper around a TSV file to function as a database
 Home-page: https://github.com/yufei-pan/TSVZ
 Author: Yufei Pan

{tsvz-3.23 → tsvz-3.25}/TSVZ.py

@@ -22,7 +22,7 @@ if os.name == 'nt':
 elif os.name == 'posix':
     import fcntl
 
-version = '3.23'
+version = '3.25'
 __version__ = version
 author = 'pan@zopyr.us'
 
@@ -128,6 +128,7 @@ def pretty_format_table(data, delimiter = DEFAULT_DELIMITER,header = None):
 def format_bytes(size, use_1024_bytes=None, to_int=False, to_str=False,str_format='.2f'):
 	"""
 	Format the size in bytes to a human-readable format or vice versa.
+	From hpcp: https://github.com/yufei-pan/hpcp
 
 	Args:
 		size (int or str): The size in bytes or a string representation of the size.
@@ -140,10 +141,16 @@ def format_bytes(size, use_1024_bytes=None, to_int=False, to_str=False,str_forma
 		int or str: The formatted size based on the provided arguments.
 
 	Examples:
-		>>> format_bytes(1500)
-		'1.50 KB'
+		>>> format_bytes(1500, use_1024_bytes=False)
+		'1.50 K'
 		>>> format_bytes('1.5 GiB', to_int=True)
 		1610612736
+		>>> format_bytes('1.5 GiB', to_str=True)
+		'1.50 Gi'
+		>>> format_bytes(1610612736, use_1024_bytes=True, to_str=True)
+		'1.50 Gi'
+		>>> format_bytes(1610612736, use_1024_bytes=False, to_str=True)
+		'1.61 G'
 	"""
 	if to_int or isinstance(size, str):
 		if isinstance(size, int):
@@ -152,6 +159,8 @@ def format_bytes(size, use_1024_bytes=None, to_int=False, to_str=False,str_forma
 			# Use regular expression to split the numeric part from the unit, handling optional whitespace
 			match = re.match(r"(\d+(\.\d+)?)\s*([a-zA-Z]*)", size)
 			if not match:
+				if to_str:
+					return size
 				print("Invalid size format. Expected format: 'number [unit]', e.g., '1.5 GiB' or '1.5GiB'")
 				print(f"Got: {size}")
 				return 0
@@ -171,8 +180,12 @@ def format_bytes(size, use_1024_bytes=None, to_int=False, to_str=False,str_forma
 				power = 10**3
 			unit_labels = {'': 0, 'k': 1, 'm': 2, 'g': 3, 't': 4, 'p': 5}
 			if unit not in unit_labels:
+				if to_str:
+					return size
 				print(f"Invalid unit '{unit}'. Expected one of {list(unit_labels.keys())}")
 				return 0
+			if to_str:
+				return format_bytes(size=int(number * (power ** unit_labels[unit])), use_1024_bytes=use_1024_bytes, to_str=True, str_format=str_format)
 			# Calculate the bytes
 			return int(number * (power ** unit_labels[unit]))
 		else:
@@ -183,8 +196,8 @@ def format_bytes(size, use_1024_bytes=None, to_int=False, to_str=False,str_forma
 	elif to_str or isinstance(size, int) or isinstance(size, float):
 		if isinstance(size, str):
 			try:
-				size = size.lower().strip().rstrip('b')
-				size = float(size)
+				size = size.rstrip('B').rstrip('b')
+				size = float(size.lower().strip())
 			except Exception as e:
 				return size
 		# size is in bytes
@@ -195,7 +208,7 @@ def format_bytes(size, use_1024_bytes=None, to_int=False, to_str=False,str_forma
 			while size > power:
 				size /= power
 				n += 1
-			return f"{size:{str_format}} {power_labels[n]}"
+			return f"{size:{str_format}}{' '}{power_labels[n]}"
 		else:
 			power = 10**3
 			n = 0
@@ -203,7 +216,7 @@ def format_bytes(size, use_1024_bytes=None, to_int=False, to_str=False,str_forma
 			while size > power:
 				size /= power
 				n += 1
-			return f"{size:{str_format}} {power_labels[n]}"
+			return f"{size:{str_format}}{' '}{power_labels[n]}"
 	else:
 		try:
 			return format_bytes(float(size), use_1024_bytes)
@@ -267,7 +280,7 @@ def __teePrintOrNot(message,level = 'info',teeLogger = None):
     except Exception:
         print(message,flush=True)
 
-def _processLine(line,taskDic,correctColumnNum,verbose = False,teeLogger = None,strict = True,delimiter = DEFAULT_DELIMITER,defaults = None):
+def _processLine(line,taskDic,correctColumnNum,verbose = False,teeLogger = None,strict = True,delimiter = DEFAULT_DELIMITER,defaults = ...):
     """
     Process a line of text and update the task dictionary.
 
@@ -284,7 +297,7 @@ def _processLine(line,taskDic,correctColumnNum,verbose = False,teeLogger = None,
     tuple: A tuple containing the updated correctColumnNum and the processed lineCache.
 
     """
-    if not defaults:
+    if defaults is ...:
         defaults = []
     line = line.strip(' ').strip('\x00').rstrip('\r\n')
     # we throw away the lines that start with '#'
@@ -354,7 +367,7 @@ def _processLine(line,taskDic,correctColumnNum,verbose = False,teeLogger = None,
         __teePrintOrNot(f"Key {lineCache[0]} added",teeLogger=teeLogger)
     return correctColumnNum, lineCache
 
-def read_last_valid_line(fileName, taskDic, correctColumnNum, verbose=False, teeLogger=None, strict=False,encoding = 'utf8',delimiter = ...,defaults = []):
+def read_last_valid_line(fileName, taskDic, correctColumnNum, verbose=False, teeLogger=None, strict=False,encoding = 'utf8',delimiter = ...,defaults = ...):
     """
     Reads the last valid line from a file.
 
@@ -374,6 +387,8 @@ def read_last_valid_line(fileName, taskDic, correctColumnNum, verbose=False, tee
     """
     chunk_size = 1024  # Read in chunks of 1024 bytes
     last_valid_line = []
+    if defaults is ...:
+        defaults = []
     delimiter = get_delimiter(delimiter,file_name=fileName)
     if verbose:
         __teePrintOrNot(f"Reading last line only from {fileName}",teeLogger=teeLogger)
@@ -515,7 +530,7 @@ def _verifyFileExistence(fileName,createIfNotExist = True,teeLogger = None,heade
             return False
     return True
 
-def readTSV(fileName,teeLogger = None,header = '',createIfNotExist = False, lastLineOnly = False,verifyHeader = True,verbose = False,taskDic = None,encoding = 'utf8',strict = True,delimiter = '\t',defaults = []):
+def readTSV(fileName,teeLogger = None,header = '',createIfNotExist = False, lastLineOnly = False,verifyHeader = True,verbose = False,taskDic = None,encoding = 'utf8',strict = True,delimiter = '\t',defaults = ...):
     """
     Compatibility method, calls readTabularFile. 
     Read a Tabular (CSV / TSV / NSV) file and return the data as a dictionary.
@@ -543,7 +558,7 @@ def readTSV(fileName,teeLogger = None,header = '',createIfNotExist = False, last
     """
     return readTabularFile(fileName,teeLogger = teeLogger,header = header,createIfNotExist = createIfNotExist,lastLineOnly = lastLineOnly,verifyHeader = verifyHeader,verbose = verbose,taskDic = taskDic,encoding = encoding,strict = strict,delimiter = delimiter,defaults=defaults)
 
-def readTabularFile(fileName,teeLogger = None,header = '',createIfNotExist = False, lastLineOnly = False,verifyHeader = True,verbose = False,taskDic = None,encoding = 'utf8',strict = True,delimiter = ...,defaults = []):
+def readTabularFile(fileName,teeLogger = None,header = '',createIfNotExist = False, lastLineOnly = False,verifyHeader = True,verbose = False,taskDic = None,encoding = 'utf8',strict = True,delimiter = ...,defaults = ...):
     """
     Read a Tabular (CSV / TSV / NSV) file and return the data as a dictionary.
 
@@ -570,6 +585,8 @@ def readTabularFile(fileName,teeLogger = None,header = '',createIfNotExist = Fal
     """
     if taskDic is None:
         taskDic = {}
+    if defaults is ...:
+        defaults = []
     delimiter = get_delimiter(delimiter,file_name=fileName)
     header = _formatHeader(header,verbose = verbose,teeLogger = teeLogger, delimiter = delimiter)
     if not _verifyFileExistence(fileName,createIfNotExist = createIfNotExist,teeLogger = teeLogger,header = header,encoding = encoding,strict = strict,delimiter=delimiter):