csvpath 0.0.499__tar.gz → 0.0.501__tar.gz

{csvpath-0.0.499 → csvpath-0.0.501}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: csvpath
-Version: 0.0.499
+Version: 0.0.501
 Summary: A declarative language for validating CSV, Excel, and other tabular data files
 Author: David Kershaw
 Author-email: dk107dk@hotmail.com
@@ -43,7 +43,7 @@ Project-URL: Github, https://github.com/csvpath/csvpath.git
 Description-Content-Type: text/markdown
 
 
-# <a href='https://www.csvpath.org/'><img src='https://github.com/csvpath/csvpath/blob/main/docs/images/csvpath-icon-sm.png'/></a> About CsvPath
+# <a href='https://www.csvpath.org/'><img src='https://github.com/csvpath/csvpath/blob/main/docs/images/logo-wordmark-4.svg'/></a>
 
 The CsvPath language defines a declarative syntax for inspecting and validating CSV and Excel files, and other tabular data.
 
@@ -70,7 +70,7 @@ CsvPath is intended to fit with other DataOps and data quality tools. Files are
 
 Read more about CsvPath and see CSV, Excel, and Data Frames validation examples at <a href='https://www.csvpath.org'>https://www.csvpath.org</a>.
 
-If you need help, use the <a href='https://www.csvpath.org/getting-started/get-help'>contact form</a> or the <a href='https://github.com/csvpath/csvpath/issues'>issue tracker</a> or talk to one of our [sponsors](#sponsors).
+If you need help, use the <a href='https://www.csvpath.org/getting-started/get-help'>contact form</a> or the <a href='https://github.com/csvpath/csvpath/issues'>issue tracker</a> or talk to one of our [sponsors, below](#sponsors).
 
 ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/csvpath?logoColor=green&color=green) ![GitHub commit activity](https://img.shields.io/github/commit-activity/m/dk107dk/csvpath) ![PyPI - Version](https://img.shields.io/pypi/v/csvpath)
 

{csvpath-0.0.499 → csvpath-0.0.501}/README.md

@@ -1,5 +1,5 @@
 
-# <a href='https://www.csvpath.org/'><img src='https://github.com/csvpath/csvpath/blob/main/docs/images/csvpath-icon-sm.png'/></a> About CsvPath
+# <a href='https://www.csvpath.org/'><img src='https://github.com/csvpath/csvpath/blob/main/docs/images/logo-wordmark-4.svg'/></a>
 
 The CsvPath language defines a declarative syntax for inspecting and validating CSV and Excel files, and other tabular data.
 
@@ -26,7 +26,7 @@ CsvPath is intended to fit with other DataOps and data quality tools. Files are
 
 Read more about CsvPath and see CSV, Excel, and Data Frames validation examples at <a href='https://www.csvpath.org'>https://www.csvpath.org</a>.
 
-If you need help, use the <a href='https://www.csvpath.org/getting-started/get-help'>contact form</a> or the <a href='https://github.com/csvpath/csvpath/issues'>issue tracker</a> or talk to one of our [sponsors](#sponsors).
+If you need help, use the <a href='https://www.csvpath.org/getting-started/get-help'>contact form</a> or the <a href='https://github.com/csvpath/csvpath/issues'>issue tracker</a> or talk to one of our [sponsors, below](#sponsors).
 
 ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/csvpath?logoColor=green&color=green) ![GitHub commit activity](https://img.shields.io/github/commit-activity/m/dk107dk/csvpath) ![PyPI - Version](https://img.shields.io/pypi/v/csvpath)
 

{csvpath-0.0.499 → csvpath-0.0.501}/config/config.ini

@@ -25,11 +25,13 @@ path = cache
 imports = config/functions.imports
 
 [listeners]
+groups=marquez,slack
+
 #uncomment for OpenLineage events to a local Marquez
-#file = from csvpath.managers.files.file_listener_ol import OpenLineageFileListener
-#paths = from csvpath.managers.paths.paths_listener_ol import OpenLineagePathsListener
-#result = from csvpath.managers.results.result_listener_ol import OpenLineageResultListener
-#results = from csvpath.managers.results.results_listener_ol import OpenLineageResultsListener
+#marquez.file = from csvpath.managers.files.file_listener_ol import OpenLineageFileListener
+#marquez.paths = from csvpath.managers.paths.paths_listener_ol import OpenLineagePathsListener
+#marquez.result = from csvpath.managers.results.result_listener_ol import OpenLineageResultListener
+#marquez.results = from csvpath.managers.results.results_listener_ol import OpenLineageResultsListener
 
 [marquez]
 base_url = http://localhost:5000

{csvpath-0.0.499 → csvpath-0.0.501}/csvpath/cli/cli.py

@@ -3,13 +3,13 @@ import os
 import time
 import traceback
 from bullet import Bullet
-from csvpath import CsvPath, CsvPaths
+from csvpath import CsvPaths
 from .drill_down import DrillDown
 
 
 class Cli:
     def __init__(self):
-        self._csvpaths = CsvPaths()
+        self.csvpaths = CsvPaths()
 
     def clear(self):
         print(chr(27) + "[2J")
@@ -35,7 +35,7 @@ class Cli:
     def _response(self, text: str) -> None:
         sys.stdout.write(f"\u001b[30;1m{text}{Cli.REVERT}\n")
 
-    def _action(self, text: str) -> None:
+    def action(self, text: str) -> None:
         sys.stdout.write(f"\033[36m{text}{Cli.REVERT}\n")
 
     def _input(self, prompt: str) -> str:
@@ -80,9 +80,9 @@ class Cli:
                 return
 
     def _do(self, t: str) -> str | None:
+        if t == "quit":
+            return t
         try:
-            if t == "quit":
-                return t
             if t == "run":
                 self.run()
             if t == "named-files":
@@ -112,8 +112,6 @@ class Cli:
             DrillDown(self).name_paths()
         if t == "list named-paths":
             self.list_named_paths()
-        if t == "cancel":
-            return
 
     def _results(self) -> None:
         choices = ["open named-result", "list named-results", "cancel"]
@@ -125,7 +123,7 @@ class Cli:
 
     def list_named_results(self):
         self.clear()
-        names = self._csvpaths.results_manager.list_named_results()
+        names = self.csvpaths.results_manager.list_named_results()
         print(f"{len(names)} named-results names:")
         for n in names:
             self._response(f"   {n}")
@@ -134,15 +132,15 @@ class Cli:
     def open_named_result(self):
         self.clear()
         try:
-            names = self._csvpaths.results_manager.list_named_results()
+            names = self.csvpaths.results_manager.list_named_results()
             print(f"{len(names)} named-results names:")
             names.append(self.CANCEL)
             cli = Bullet(bullet=" > ", choices=names)
             t = cli.launch()
             if t == self.CANCEL:
                 return
-            t = f"{self._csvpaths.config.archive_path}{os.sep}{t}"
-            self._action(f"Opening results at {t}...")
+            t = f"{self.csvpaths.config.archive_path}{os.sep}{t}"
+            self.action(f"Opening results at {t}...")
             self.short_pause()
             c = f"open {t}"
             os.system(c)
@@ -151,7 +149,7 @@ class Cli:
 
     def list_named_paths(self):
         self.clear()
-        names = self._csvpaths.paths_manager.named_paths_names
+        names = self.csvpaths.paths_manager.named_paths_names
         names.sort()
         print(f"{len(names)} named-paths names:")
         for n in names:
@@ -160,7 +158,7 @@ class Cli:
 
     def list_named_files(self):
         self.clear()
-        names = self._csvpaths.file_manager.named_file_names
+        names = self.csvpaths.file_manager.named_file_names
         names.sort()
         print(f"{len(names)} named-file names:")
         for n in names:
@@ -170,12 +168,12 @@ class Cli:
     def run(self):
         self.clear()
         print("What named-file? ")
-        files = self._csvpaths.file_manager.named_file_names
+        files = self.csvpaths.file_manager.named_file_names
         cli = Bullet(bullet=" > ", choices=files)
         file = cli.launch()
         self.clear()
         print("What named-paths? ")
-        allpaths = self._csvpaths.paths_manager.named_paths_names
+        allpaths = self.csvpaths.paths_manager.named_paths_names
         cli = Bullet(bullet=" > ", choices=allpaths)
         paths = cli.launch()
         self.clear()
@@ -183,13 +181,13 @@ class Cli:
         cli = Bullet(bullet=" > ", choices=["collect", "fast-forward"])
         method = cli.launch()
         self.clear()
-        self._action(f"Running {paths} against {file} using {method}\n")
+        self.action(f"Running {paths} against {file} using {method}\n")
         self.pause()
         try:
             if method == "collect":
-                self._csvpaths.collect_paths(filename=file, pathsname=paths)
+                self.csvpaths.collect_paths(filename=file, pathsname=paths)
             else:
-                self._csvpaths.fast_forward_paths(filename=file, pathsname=paths)
+                self.csvpaths.fast_forward_paths(filename=file, pathsname=paths)
         except Exception:
             print(traceback.format_exc())
         self._return_to_cont()

{csvpath-0.0.499 → csvpath-0.0.501}/csvpath/cli/drill_down.py

@@ -1,5 +1,3 @@
-from csvpath import CsvPath, CsvPaths
-import sys
 import os
 from bullet import Bullet
 
@@ -22,21 +20,21 @@ class DrillDown:
         # get path
         #
         t = self._get_add_type()
-        p = self._get_path(t, self._cli._csvpaths.config.csv_file_extensions)
+        p = self._get_path(t, self._cli.csvpaths.config.csv_file_extensions)
         if p is False:
             return
         #
         # do the add
         #
         self._cli.clear()
-        self._cli._action(f"Adding: {p}\n")
+        self._cli.action(f"Adding: {p}\n")
         self._cli.pause()
         if t == "file":
-            self._cli._csvpaths.file_manager.add_named_file(name=name, path=p)
+            self._cli.csvpaths.file_manager.add_named_file(name=name, path=p)
         elif t == "dir":
-            self._cli._csvpaths.file_manager.add_named_files_from_dir(dirname=p)
+            self._cli.csvpaths.file_manager.add_named_files_from_dir(dirname=p)
         else:
-            self._cli._csvpaths.file_manager.set_named_files_from_json(
+            self._cli.csvpaths.file_manager.set_named_files_from_json(
                 name=name, filename=p
             )
 
@@ -54,7 +52,7 @@ class DrillDown:
         # get path
         #
         t = self._get_add_type()
-        exts = self._cli._csvpaths.config.csvpath_file_extensions
+        exts = self._cli.csvpaths.config.csvpath_file_extensions
         p = self._get_path(t, exts)
         if p is False:
             return
@@ -62,14 +60,14 @@ class DrillDown:
         # do the add
         #
         self._cli.clear()
-        self._cli._action(f"Adding: {p}\n")
+        self._cli.action(f"Adding: {p}\n")
         self._cli.pause()
         if t == "file":
-            self._cli._csvpaths.paths_manager.add_named_paths(name=name, from_file=p)
+            self._cli.csvpaths.paths_manager.add_named_paths(name=name, from_file=p)
         elif t == "dir":
-            self._cli._csvpaths.paths_manager.add_named_paths(name=name, from_dir=p)
+            self._cli.csvpaths.paths_manager.add_named_paths(name=name, from_dir=p)
         else:
-            self._cli._csvpaths.paths_manager.add_named_paths(name=name, from_json=p)
+            self._cli.csvpaths.paths_manager.add_named_paths(name=name, from_json=p)
 
     # ============================
     # Utilities
@@ -85,7 +83,7 @@ class DrillDown:
             extensions.append("")
         while p is not None and p != "" and not os.path.isfile(p):
             self._cli.clear()
-            self._cli._action(f"{p}\n")
+            self._cli.action(f"{p}\n")
             p = self._drill_down(
                 path=p,
                 json=True if t == "json" else False,

{csvpath-0.0.499 → csvpath-0.0.501}/csvpath/csvpath.py

@@ -1,7 +1,6 @@
 """ CsvPath is the main class for the library. most of the magic
-    happens either here or in individual functions. """
+    happens either here or in individual functions. """  # pylint: disable=C0302
 
-import csv
 import time
 import os
 import hashlib
@@ -9,9 +8,13 @@ from datetime import datetime, timezone
 from typing import List, Dict, Any
 from collections.abc import Iterator
 from abc import ABC, abstractmethod
-from csvpath.util.config import Config
-from csvpath.util.line_monitor import LineMonitor
-from csvpath.util.log_utility import LogUtility
+from .util.config import Config
+from .util.line_monitor import LineMonitor
+from .util.log_utility import LogUtility
+from .util.printer import Printer
+from .util.file_readers import DataFileReader
+from .util.line_spooler import LineSpooler, ListLineSpooler
+from .modes.mode_controller import ModeController
 from .matching.matcher import Matcher
 from .scanning.scanner import Scanner
 from .util.metadata_parser import MetadataParser
@@ -26,10 +29,6 @@ from .util.exceptions import (
     CsvPathsException,
 )
 from .matching.util.exceptions import MatchException
-from csvpath.util.printer import Printer
-from csvpath.util.file_readers import DataFileReader
-from csvpath.util.line_spooler import LineSpooler, ListLineSpooler
-from csvpath.modes.mode_controller import ModeController
 
 
 class CsvPathPublic(ABC):
@@ -327,12 +326,12 @@ class CsvPath(CsvPathPublic, ErrorCollector, Printer):  # pylint: disable=R0902,
 
     @will_run.setter
     def will_run(self, mode) -> None:
-        self.self.modes.run_mode.value = mode
+        self.modes.run_mode.value = mode
 
     #
     # increases the total accumulated time spent doing c.matches() by t
     #
-    def _up_function_time_match(self, c, t) -> None:
+    def up_function_time_match(self, c, t) -> None:
         if c not in self.function_times_match:
             self.function_times_match[c] = 0
         st = self.function_times_match[c]
@@ -346,7 +345,7 @@ class CsvPath(CsvPathPublic, ErrorCollector, Printer):  # pylint: disable=R0902,
     #
     # increases the total accumulated time spent doing c.to_value() by t
     #
-    def _up_function_time_value(self, c, t) -> None:
+    def up_function_time_value(self, c, t) -> None:
         if c not in self.function_times_value:
             self.function_times_value[c] = 0
         st = self.function_times_value[c]
@@ -406,29 +405,39 @@ class CsvPath(CsvPathPublic, ErrorCollector, Printer):  # pylint: disable=R0902,
 
     @property
     def identity(self) -> str:
-        """returns id or name if found in metadata. the id or name gets
-        into metadata primarily if found in an "external" comment in
-        the csvpath. "external" meaning outside the []s. comments are
-        keyword:comment. we take id, Id, ID and name, Name, NAME. id
-        is preferred over name. E.g.:
-        ~ name: my path description: an example ~
+        """returns id or name if found in metadata.
+
+        the id or name gets into metadata primarily if found
+        in an "external" comment in the csvpath. "external"
+        meaning outside the []s. comments are keyword:comment.
+        we take id, Id, ID and name, Name, NAME.
+
+        id is preferred over name. E.g. in:
+        ~ name: my path description: an example id: this value wins ~
+        the id becomes the identity of the instance.
+
+        we prefer in this order: all-lower most, Initial-caps,
+        ALL-CAPS least
+
+        the ordering is relied on in Result and possibly
+        elsewhere.
         """
-        # this ordering is relied on in Result and possibly elsewhere
+        ret = None
         if not self.metadata:
-            return ""
-        if "id" in self.metadata:
-            return self.metadata["id"]
-        if "Id" in self.metadata:
-            return self.metadata["Id"]
-        if "ID" in self.metadata:
-            return self.metadata["ID"]
-        if "name" in self.metadata:
-            return self.metadata["name"]
-        if "Name" in self.metadata:
-            return self.metadata["Name"]
+            ret = ""
         if "NAME" in self.metadata:
-            return self.metadata["NAME"]
-        return ""
+            ret = self.metadata["NAME"]
+        if "Name" in self.metadata:
+            ret = self.metadata["Name"]
+        if "name" in self.metadata:
+            ret = self.metadata["name"]
+        if "ID" in self.metadata:
+            ret = self.metadata["ID"]
+        if "Id" in self.metadata:
+            ret = self.metadata["Id"]
+        if "id" in self.metadata:
+            ret = self.metadata["id"]
+        return ret
 
     @property
     def config(self) -> Config:  # pylint: disable=C0116
@@ -507,7 +516,7 @@ class CsvPath(CsvPathPublic, ErrorCollector, Printer):  # pylint: disable=R0902,
     def has_default_printer(self) -> bool:
         if not self.printers:
             self.printers = []
-        for i, p in enumerate(self.printers):
+        for p in self.printers:
             if isinstance(p, StdOutPrinter):
                 return True
         return False
@@ -522,15 +531,17 @@ class CsvPath(CsvPathPublic, ErrorCollector, Printer):  # pylint: disable=R0902,
 
     @property
     def last_line(self):
+        """this method only returns the default printer's last_line"""
         if not self.printers or len(self.printers) == 0:
             return None
         return self.printers[0].last_line
 
     @property
     def lines_printed(self) -> int:
+        """this method only returns the default printer's lines printed"""
         if not self.printers or len(self.printers) == 0:
             return -1
-        self.printers[0].lines_printed
+        return self.printers[0].lines_printed
 
     @property
     def is_frozen(self) -> bool:
@@ -631,10 +642,12 @@ class CsvPath(CsvPathPublic, ErrorCollector, Printer):  # pylint: disable=R0902,
         #   - files-mode: all | no-data | no-unmatched | no-printouts | data | unmatched | errors | meta | vars | printouts
         #
         self.modes.update()
-        # self.update_arg_validation_mode_if()
 
     # =====================
-
+    # in principle the modes should come through the mode controller like:
+    #      self.modes.transfer_mode.value
+    # not wading into that today. low value.
+    #
     @property
     def transfer_mode(self) -> str:
         return self.metadata.get("transfer-mode")
@@ -774,7 +787,7 @@ class CsvPath(CsvPathPublic, ErrorCollector, Printer):  # pylint: disable=R0902,
         i = data.find("]")
         if i < 0:
             raise InputException(f"Cannot find the scan part of this csvpath: {data}")
-        elif i == len(data) - 1:
+        if i == len(data) - 1:
             raise InputException(
                 f"The scan part of this csvpath cannot be last: {data}"
             )
@@ -787,7 +800,6 @@ class CsvPath(CsvPathPublic, ErrorCollector, Printer):  # pylint: disable=R0902,
 
         if ndata == "":
             raise InputException(f"There must be a match part of this csvpath: {data}")
-
         if ndata[0] != "[":
             raise InputException(f"Cannot find the match part of this csvpath: {data}")
         if ndata[len(ndata) - 1] != "]":
@@ -1024,7 +1036,12 @@ class CsvPath(CsvPathPublic, ErrorCollector, Printer):  # pylint: disable=R0902,
         #
         if self.scanner.filename is None:
             raise FileException("There is no filename")
-        reader = DataFileReader(
+        #
+        # DataFileReader is abstract. instantiating it results in a concrete subclass.
+        # pylint doesn't like that just because it doesn't see what we're doing.
+        # otoh, is this a bad way to do it? not sure but it works fine.
+        #
+        reader = DataFileReader(  # pylint: disable=E0110
             self.scanner.filename, delimiter=self.delimiter, quotechar=self.quotechar
         )
         for line in reader.next():
@@ -1032,35 +1049,6 @@ class CsvPath(CsvPathPublic, ErrorCollector, Printer):  # pylint: disable=R0902,
             yield line
         self.finalize()
 
-    """
-    # potential replacement for method above
-    # this is a proposal for having the results of one csvpath feed into another
-    # in memory. the goal being to both shape the data chain-of-responsibility-style
-    # and also to narrow the data for performance gains.
-    #
-    # we would need:
-    #   - csvpaths.chain_result_data
-    #   - named-path added to csvpath metadata early-on
-    #
-    # caching this here for now. jury is out on if it should be added.
-    #
-    def _next_line_new(self) -> List[Any]:
-        self.logger.info("beginning to scan file: %s", self.scanner.filename)
-        if self.csvpath and self.csvpaths.chain_result_data:
-            rs = csvpath.result_manager.get_named_results(self.metadata["named-paths"])
-            for line in rs[len(rs)-1].lines:
-                yield line
-        elif:
-            with open(self.scanner.filename, "r", encoding="utf-8") as file:
-                reader = csv.reader(
-                    file, delimiter=self.delimiter, quotechar=self.quotechar
-                )
-                for line in reader:
-                    self.track_line(line=line)
-                    yield line
-        self.finalize()
-    """
-
     def finalize(self) -> None:
         """clears caches, etc. this is an internal method, but not _ because
         it is part of the lifecycle and we might find a reason to call it
@@ -1176,8 +1164,7 @@ class CsvPath(CsvPathPublic, ErrorCollector, Printer):  # pylint: disable=R0902,
                 raise InputException(
                     f"[{self.identity}] Line {self.line_monitor.physical_line_number}: unknown header name: {k}"
                 )
-            else:
-                ls.append(line[k])
+            ls.append(line[k])
         return ls
 
     def advance(self, ff: int = -1) -> None:
@@ -1210,12 +1197,12 @@ class CsvPath(CsvPathPublic, ErrorCollector, Printer):  # pylint: disable=R0902,
             self.get_total_lines_and_headers()
         return self.line_monitor.physical_end_line_number
 
-    def get_total_lines_and_headers(self) -> int:  # pylint: disable=C0116
+    def get_total_lines_and_headers(self) -> None:  # pylint: disable=C0116
         if not self.scanner or not self.scanner.filename:
             self.logger.error(
-                f"Csvpath identified as {self.identity} has no filename. Since that can happen during error handling an exception won't be raised."
+                "Csvpath identified as %s has no filename. Since we could be error handling an exception is not raised.",
+                self.identity,
             )
-            return -1
         if self.csvpaths:
             self.line_monitor = self.csvpaths.file_manager.cacher.get_new_line_monitor(
                 self.scanner.filename

{csvpath-0.0.499 → csvpath-0.0.501}/csvpath/csvpaths.py

@@ -3,7 +3,6 @@
 
 from abc import ABC, abstractmethod
 from typing import List, Any
-import csv
 import traceback
 from datetime import datetime, timezone
 from .util.error import ErrorHandler, ErrorCollector, Error
@@ -151,6 +150,8 @@ class CsvPaths(CsvPathsPublic, CsvPathsCoordinator, ErrorCollector):
         self._run_time_str = None
 
     def run_time_str(self, pathsname=None) -> str:
+        """adds the stringified current run time to the named-paths
+        group home_dir to create the run_dir"""
         if self._run_time_str is None and pathsname is None:
             raise CsvPathsException(
                 "Cannot have None in both run_time_str and pathsname"
@@ -163,6 +164,7 @@ class CsvPaths(CsvPathsPublic, CsvPathsCoordinator, ErrorCollector):
 
     @property
     def current_run_time(self) -> datetime:
+        """gets the time marking the start of the run. used to create the run home directory."""
         if self._current_run_time is None:
             self._current_run_time = datetime.now(timezone.utc)
         return self._current_run_time
@@ -294,7 +296,7 @@ class CsvPaths(CsvPathsPublic, CsvPathsCoordinator, ErrorCollector):
                     ErrorHandler(
                         csvpaths=self, csvpath=csvpath, error_collector=result
                     ).handle_error(ex)
-                except Exception as e:
+                except Exception as e:  # pylint: disable=W0718
                     self.results_manager.save(result)
                     raise e
             self.results_manager.save(result)
@@ -410,6 +412,7 @@ class CsvPaths(CsvPathsPublic, CsvPathsCoordinator, ErrorCollector):
         self.logger.debug("Done loading csvpath")
 
     def fast_forward_paths(self, *, pathsname, filename):
+        """runs the named-paths group named without collecting matches."""
         paths = self.paths_manager.get_named_paths(pathsname)
         file = self.file_manager.get_named_file(filename)
         self.logger.info("Prepping %s and %s", filename, pathsname)
@@ -471,7 +474,7 @@ class CsvPaths(CsvPathsPublic, CsvPathsCoordinator, ErrorCollector):
                     ErrorHandler(
                         csvpaths=self, csvpath=csvpath, error_collector=result
                     ).handle_error(ex)
-                except Exception as e:
+                except Exception as e:  # pylint: disable=W0718
                     self.results_manager.save(result)
                     raise e
             self.results_manager.save(result)
@@ -487,7 +490,9 @@ class CsvPaths(CsvPathsPublic, CsvPathsCoordinator, ErrorCollector):
             "Completed fast_forward_paths %s with %s paths", pathsname, len(paths)
         )
 
-    def next_paths(self, *, pathsname, filename, collect: bool = False):
+    def next_paths(
+        self, *, pathsname, filename, collect: bool = False
+    ):  # pylint: disable=R0914
         """appends the Result for each CsvPath to the end of
         each line it produces. this is so that the caller can easily
         interrogate the CsvPath for its path parts, file, etc."""
@@ -562,14 +567,14 @@ class CsvPaths(CsvPathsPublic, CsvPathsCoordinator, ErrorCollector):
                         result.append(line)
                         result.unmatched = csvpath.unmatched
                     yield line
-            except Exception as ex:
+            except Exception as ex:  # pylint: disable=W0718
                 ex.trace = traceback.format_exc()
                 ex.source = self
                 try:
                     ErrorHandler(
                         csvpaths=self, csvpath=csvpath, error_collector=result
                     ).handle_error(ex)
-                except Exception as e:
+                except Exception as e:  # pylint: disable=W0718
                     self.results_manager.save(result)
                     raise e
 
@@ -636,7 +641,7 @@ class CsvPaths(CsvPathsPublic, CsvPathsCoordinator, ErrorCollector):
             filename,
         )
 
-    def next_by_line(  # pylint: disable=R0912
+    def next_by_line(  # pylint: disable=R0912,R0915,R0914
         self,
         *,
         pathsname,
@@ -780,7 +785,7 @@ class CsvPaths(CsvPathsPublic, CsvPathsCoordinator, ErrorCollector):
                         csvpath=self.current_matcher,
                         error_collector=self.current_matcher,
                     ).handle_error(ex)
-                except Exception as e:
+                except Exception as e:  # pylint: disable=W0718
                     for r in csvpath_objects:
                         result = r[1]
                         result.unmatched = r[0].unmatched

{csvpath-0.0.499 → csvpath-0.0.501}/csvpath/managers/files/file_listener_ol.py

@@ -1,4 +1,4 @@
-from ..ol.ol_listener import OpenLineageListener
+from ..integrations.ol.ol_listener import OpenLineageListener
 
 
 class OpenLineageFileListener(OpenLineageListener):

{csvpath-0.0.499 → csvpath-0.0.501}/csvpath/managers/files/file_manager.py

@@ -162,7 +162,6 @@ class FileManager:
         self.registrar.register_complete(mdata)
 
     def _copy_in(self, path, home) -> None:
-        # fname = self._simple_name(path)
         fname = path if path.rfind(os.sep) == -1 else path[path.rfind(os.sep) + 1 :]
         # creates
         #   a/file.csv -> named_files/name/file.csv/file.csv

{csvpath-0.0.499 → csvpath-0.0.501}/csvpath/managers/files/file_registrar.py

@@ -18,7 +18,7 @@ class FileRegistrar(Registrar, Listener):
         super().__init__(csvpaths)
         self.csvpaths = csvpaths
         self.config = csvpaths.config
-        self.load_additional_listeners("file")
+        self.type = "file"
 
     def get_fingerprint(self, home) -> str:
         mpath = self.manifest_path(home)
@@ -110,6 +110,9 @@ class FileRegistrar(Registrar, Listener):
                 and "file_home" in _
                 and _["file_home"] == mdata.file_home
             ):
+                #
+                # leave as info so nobody has to dig to see why no update
+                #
                 self.csvpaths.logger.info("File has already been registered: %s", jdata)
                 return
         self.distribute_update(mdata)

{csvpath-0.0.499/csvpath/managers → csvpath-0.0.501/csvpath/managers/integrations}/ol/event.py

@@ -11,12 +11,12 @@ from openlineage.client.event_v2 import Dataset, RunEvent
 from openlineage.client.event_v2 import Job, Run, RunState
 from openlineage.client.event_v2 import InputDataset, OutputDataset
 
-from ..metadata import Metadata
-from ..results.results_metadata import ResultsMetadata
-from ..results.result_metadata import ResultMetadata
-from ..paths.paths_metadata import PathsMetadata
-from ..files.file_metadata import FileMetadata
-from ..run.run_metadata import RunMetadata
+from csvpath.managers.metadata import Metadata
+from csvpath.managers.results.results_metadata import ResultsMetadata
+from csvpath.managers.results.result_metadata import ResultMetadata
+from csvpath.managers.paths.paths_metadata import PathsMetadata
+from csvpath.managers.files.file_metadata import FileMetadata
+from csvpath.managers.run.run_metadata import RunMetadata
 
 from .job import JobBuilder
 from .run import RunBuilder