TSVZ 3.35__tar.gz → 3.37__tar.gz

{tsvz-3.35 → tsvz-3.37}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: TSVZ
-Version: 3.35
+Version: 3.37
 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 +11,9 @@ Classifier: License :: OSI Approved :: GNU General Public License v3 or later (G
 Classifier: Operating System :: OS Independent
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
+Requires-Dist: argparse
+Provides-Extra: completion
+Requires-Dist: argcomplete; extra == "completion"
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -18,6 +21,8 @@ Dynamic: description
 Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: license
+Dynamic: provides-extra
+Dynamic: requires-dist
 Dynamic: requires-python
 Dynamic: summary
 

{tsvz-3.35 → tsvz-3.37}/TSVZ.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: TSVZ
-Version: 3.35
+Version: 3.37
 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 +11,9 @@ Classifier: License :: OSI Approved :: GNU General Public License v3 or later (G
 Classifier: Operating System :: OS Independent
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
+Requires-Dist: argparse
+Provides-Extra: completion
+Requires-Dist: argcomplete; extra == "completion"
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -18,6 +21,8 @@ Dynamic: description
 Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: license
+Dynamic: provides-extra
+Dynamic: requires-dist
 Dynamic: requires-python
 Dynamic: summary
 

{tsvz-3.35 → tsvz-3.37}/TSVZ.egg-info/SOURCES.txt

@@ -5,4 +5,6 @@ TSVZ.egg-info/PKG-INFO
 TSVZ.egg-info/SOURCES.txt
 TSVZ.egg-info/dependency_links.txt
 TSVZ.egg-info/entry_points.txt
-TSVZ.egg-info/top_level.txt
+TSVZ.egg-info/requires.txt
+TSVZ.egg-info/top_level.txt
+tests/test_regression.py

tsvz-3.37/TSVZ.egg-info/requires.txt

@@ -0,0 +1,4 @@
+argparse
+
+[completion]
+argcomplete

{tsvz-3.35 → tsvz-3.37}/TSVZ.py

@@ -1,4 +1,5 @@
-#!/usr/bin/env python3
+#! /usr/bin/env python3
+# PYTHON_ARGCOMPLETE_OK
 # /// script
 # requires-python = ">=3.6"
 # dependencies = [
@@ -26,15 +27,15 @@ if os.name == 'nt':
 elif os.name == 'posix':
 	import fcntl
 
-version = '3.35'
+version = '3.37'
 __version__ = version
 author = 'pan@zopyr.us'
-COMMIT_DATE = '2025-11-13'
+COMMIT_DATE = '2026-04-21'
 
 DEFAULT_DELIMITER = '\t'
 DEFAULTS_INDICATOR_KEY = '#_defaults_#'
 
-COMPRESSED_FILE_EXTENSIONS = ['gz','gzip','bz2','bzip2','xz','lzma']
+COMPRESSED_FILE_EXTENSIONS = ['gz','gzip','bz2','bzip2','xz','lzma','zst','zstd']
 
 def get_delimiter(delimiter,file_name = ''):
 	global DEFAULT_DELIMITER
@@ -75,34 +76,43 @@ def eprint(*args, **kwargs):
 		print(*args, **kwargs)
 
 def openFileAsCompressed(fileName,mode = 'rb',encoding = 'utf8',teeLogger = None,compressLevel = 1):
+	lowerFileName = fileName.lower()
 	if 'b' not in mode:
 		mode += 't'
 	kwargs = {}
 	if 'r' not in mode:
-		if fileName.endswith('.xz'):
+		if lowerFileName.endswith('.xz'):
 			kwargs['preset'] = compressLevel
+		elif lowerFileName.endswith('.zst') or lowerFileName.endswith('.zstd'):
+			kwargs['level'] = compressLevel
 		else:
 			kwargs['compresslevel'] = compressLevel
 	if 'b' not in mode:
 		kwargs['encoding'] = encoding
-	if fileName.endswith('.xz') or fileName.endswith('.lzma'):
+	if lowerFileName.endswith('.xz') or lowerFileName.endswith('.lzma'):
 		try:
 			import lzma
 			return lzma.open(fileName, mode, **kwargs)
 		except Exception:
 			__teePrintOrNot(f"Failed to open {fileName} with lzma, trying bin",teeLogger=teeLogger)
-	elif fileName.endswith('.gz') or fileName.endswith('.gzip'):
+	elif lowerFileName.endswith('.gz') or lowerFileName.endswith('.gzip'):
 		try:
 			import gzip
 			return gzip.open(fileName, mode, **kwargs)
 		except Exception:
 			__teePrintOrNot(f"Failed to open {fileName} with gzip, trying bin",teeLogger=teeLogger)
-	elif fileName.endswith('.bz2') or fileName.endswith('.bzip2'):
+	elif lowerFileName.endswith('.bz2') or lowerFileName.endswith('.bzip2'):
 		try:
 			import bz2
 			return bz2.open(fileName, mode, **kwargs)
 		except Exception:
 			__teePrintOrNot(f"Failed to open {fileName} with bz2, trying bin",teeLogger=teeLogger)
+	elif lowerFileName.endswith('.zst') or lowerFileName.endswith('.zstd'):
+		try:
+			from compression import zstd
+			return zstd.open(fileName, mode, **kwargs)
+		except Exception:
+			__teePrintOrNot(f"Failed to open {fileName} with zstd, trying bin",teeLogger=teeLogger)
 	if 't' in mode:
 		mode = mode.replace('t','')
 		return open(fileName, mode, encoding=encoding)
@@ -545,8 +555,9 @@ def read_last_valid_line(fileName, taskDic, correctColumnNum, verbose=False, tee
 					)
 					# If the line is valid, return it
 					if lineCache:
-						if storeOffset and any(lineCache):
-							return lineCache
+						if storeOffset :
+							return file_size - processedSize + 1
+						return lineCache
 			
 			# Keep the last (possibly incomplete) line in buffer for the next read
 			buffer = lines[0]
@@ -2260,6 +2271,11 @@ def __main__():
 	strictMode.add_argument('-f', '--force', dest = 'strict',action='store_false', help='Force the operation. Ignore checks for column numbers / headers')
 	parser.add_argument('-v', '--verbose', action='store_true', help='Print verbose output')
 	parser.add_argument('-V', '--version', action='version', version=f'%(prog)s {version} @ {COMMIT_DATE} by {author}')
+	try:
+		import argcomplete
+		argcomplete.autocomplete(parser,always_complete_options='long')
+	except ImportError:
+		pass
 	args = parser.parse_args()
 	args.delimiter = get_delimiter(delimiter=args.delimiter,file_name=args.filename)
 	if args.header and args.header.endswith('\\'):

{tsvz-3.35 → tsvz-3.37}/setup.py

@@ -15,6 +15,14 @@ setup(
 			'tsvz = TSVZ:__main__',
         ],
     },
+    install_requires=[
+        'argparse',
+    ],
+    extras_require={
+        'completion': [
+            'argcomplete',
+        ],
+    },
     classifiers=[
         'Programming Language :: Python :: 3',
         'License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)',

tsvz-3.37/tests/test_regression.py

@@ -0,0 +1,104 @@
+import os
+import sys
+import tempfile
+import unittest
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(__file__)))
+import TSVZ
+
+
+class TestTSVZRegressions(unittest.TestCase):
+    def test_append_and_read_preserves_embedded_tab_and_newline(self):
+        with tempfile.TemporaryDirectory() as temp_dir:
+            path = os.path.join(temp_dir, "embedded.tsv")
+            header = ["key", "payload"]
+            row = ["row1", "hello\tworld\nline2"]
+
+            TSVZ.appendTabularFile(
+                path,
+                row,
+                header=header,
+                createIfNotExist=True,
+                verifyHeader=True,
+                strict=True,
+                delimiter="\t",
+            )
+
+            data = TSVZ.readTabularFile(
+                path,
+                header=header,
+                verifyHeader=True,
+                strict=True,
+                delimiter="\t",
+            )
+
+            self.assertIn("row1", data)
+            self.assertEqual(data["row1"], row)
+
+    def test_read_uses_defaults_row_for_missing_values(self):
+        with tempfile.TemporaryDirectory() as temp_dir:
+            path = os.path.join(temp_dir, "defaults.tsv")
+            with open(path, "w", encoding="utf8") as handle:
+                handle.write("key\tcpu\tmem\n")
+                handle.write(f"{TSVZ.DEFAULTS_INDICATOR_KEY}\t4\t8G\n")
+                handle.write("job1\t2\t16G\n")
+                handle.write("job2\t\t32G\n")
+
+            data = TSVZ.readTabularFile(
+                path,
+                header=["key", "cpu", "mem"],
+                verifyHeader=True,
+                strict=True,
+                delimiter="\t",
+            )
+
+            self.assertEqual(data["job1"], ["job1", "2", "16G"])
+            self.assertEqual(data["job2"], ["job2", "4", "32G"])
+
+    def test_last_line_only_ignores_delete_marker_line(self):
+        with tempfile.TemporaryDirectory() as temp_dir:
+            path = os.path.join(temp_dir, "lastline.tsv")
+            with open(path, "w", encoding="utf8") as handle:
+                handle.write("key\tvalue\n")
+                handle.write("alive\t42\n")
+                handle.write("alive\n")
+
+            last_valid = TSVZ.readTabularFile(
+                path,
+                header=["key", "value"],
+                verifyHeader=True,
+                lastLineOnly=True,
+                strict=False,
+                delimiter="\t",
+            )
+
+            self.assertEqual(last_valid, ["alive", "42"])
+
+    def test_append_and_read_gzip_file(self):
+        with tempfile.TemporaryDirectory() as temp_dir:
+            path = os.path.join(temp_dir, "compressed.tsv.gz")
+            header = ["key", "value"]
+
+            TSVZ.appendTabularFile(
+                path,
+                ["gk", "gv"],
+                header=header,
+                createIfNotExist=True,
+                verifyHeader=True,
+                strict=True,
+                delimiter="\t",
+            )
+
+            data = TSVZ.readTabularFile(
+                path,
+                header=header,
+                verifyHeader=True,
+                strict=True,
+                delimiter="\t",
+            )
+
+            self.assertEqual(data["gk"], ["gk", "gv"])
+
+
+if __name__ == "__main__":
+    unittest.main()