TSVZ 2.67__tar.gz → 2.70__tar.gz

{tsvz-2.67 → tsvz-2.70}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: TSVZ
-Version: 2.67
+Version: 2.70
 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
@@ -11,6 +11,14 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: requires-python
+Dynamic: summary
 
 This lib provides some helper funtions to interact with tsv ( tab seperated values ) files.
 

{tsvz-2.67 → tsvz-2.70}/TSVZ.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: TSVZ
-Version: 2.67
+Version: 2.70
 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
@@ -11,6 +11,14 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: requires-python
+Dynamic: summary
 
 This lib provides some helper funtions to interact with tsv ( tab seperated values ) files.
 

{tsvz-2.67 → tsvz-2.70}/TSVZ.py

@@ -10,23 +10,39 @@ if os.name == 'nt':
 elif os.name == 'posix':
     import fcntl
 
-version = '2.67'
+version = '2.70'
 author = 'pan@zopyr.us'
 
 
 def pretty_format_table(data):
+	version = 1.0
 	if not data:
-		return
+		return ''
 	if type(data) == str:
 		data = data.strip('\n').split('\n')
+		data = [line.split('\t') for line in data]
+	elif isinstance(data, dict):
+		# flatten the 2D dict to a list of lists
+		if isinstance(next(iter(data.values())), dict):
+			tempData = [['key'] + list(next(iter(data.values())).keys())]
+			tempData.extend( [[key] + list(value.values()) for key, value in data.items()])
+			data = tempData
+		else:
+			# it is a dict of lists
+			data = [[key] + list(value) for key, value in data.items()]
 	elif type(data) != list:
 		data = list(data)
+	# format the list into 2d list of list of strings
+	if isinstance(data[0], dict):
+		tempData = [data[0].keys()]
+		tempData.extend([list(item.values()) for item in data])
+		data = tempData
+	data = [[str(item) for item in row] for row in data]
 	num_cols = len(data[0])
 	col_widths = [0] * num_cols
 	# Calculate the maximum width of each column
 	for c in range(num_cols):
-		col_items = [str(row[c]) for row in data]
-		col_widths[c] = max(len(item) for item in col_items)
+		col_widths[c] = max(len(row[c]) for row in data)
 	# Build the row format string
 	row_format = ' | '.join('{{:<{}}}'.format(width) for width in col_widths)
 	# Print the header
@@ -35,7 +51,11 @@ def pretty_format_table(data):
 	outTable.append(row_format.format(*header))
 	outTable.append('-+-'.join('-' * width for width in col_widths))
 	for row in data[1:]:
-		outTable.append(row_format.format(*row))
+		# if the row is empty, print an divider
+		if not any(row):
+			outTable.append('-+-'.join('-' * width for width in col_widths))
+		else:
+			outTable.append(row_format.format(*row))
 	return '\n'.join(outTable) + '\n'
 
 def __teePrintOrNot(message,level = 'info',teeLogger = None):
@@ -225,11 +245,15 @@ def lineContainHeader(header,line,verbose = False,teeLogger = None,strict = Fals
     Returns:
     bool: True if the header matches the line, False otherwise.
     """
+    escapedHeader = repr(header.strip())
+    escapedLine = repr(line.strip())
     if verbose:
-        __teePrintOrNot(f"Header: {header.strip()}",teeLogger=teeLogger)
-        __teePrintOrNot(f"First line: {line}",teeLogger=teeLogger)
-    if not line.lower().replace(' ','').startswith(header.strip().lower().replace(' ','')):
-        __teePrintOrNot(f"Header mismatch: \n{line} \n!= \n{header.strip()}",teeLogger=teeLogger)
+        __teePrintOrNot(f"Header: \n{escapedHeader}",teeLogger=teeLogger)
+        __teePrintOrNot(f"First line: \n{escapedLine}",teeLogger=teeLogger)
+    headerList = header.strip().lower().split('\t')
+    lineList = line.strip().lower().split('\t')
+    if len(headerList) != len(lineList) or any([headerList[i] not in lineList[i] for i in range(len(headerList))]):
+        __teePrintOrNot(f"Header mismatch: \n{escapedLine} \n!= \n{escapedHeader}",teeLogger=teeLogger)
         if strict:
             raise Exception("Data format error! Header mismatch")
         return False
@@ -333,6 +357,13 @@ def appendTSV(fileName,lineToAppend,teeLogger = None,header = '',createIfNotExis
         return
     if type(lineToAppend) == str:
         lineToAppend = lineToAppend.strip().split('\t')
+    else:
+        for i in range(len(lineToAppend)):
+            if type(lineToAppend[i]) != str:
+                try:
+                    lineToAppend[i] = str(lineToAppend[i])
+                except Exception as e:
+                    lineToAppend[i] = str(e)
     
     with open(fileName, mode ='r+b')as file:
         correctColumnNum = len(lineToAppend)

{tsvz-2.67 → tsvz-2.70}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup
 
 setup(
     name='TSVZ',
-    version='2.67',  
+    version='2.70',  
     py_modules=['TSVZ'],  # List of module names (without .py)
     description='An simple in memory wrapper around a TSV file to function as a database',
     author='Yufei Pan',