csvpath 0.0.559__tar.gz → 0.0.561__tar.gz

{csvpath-0.0.559 → csvpath-0.0.561}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: csvpath
-Version: 0.0.559
+Version: 0.0.561
 Summary: A data preboarding framework for managing and validating CSV, Excel, and other tabular data files using a Collect, Store, Validate, Publish pattern to create a trusted publisher for downstream data consumers.
 Author: David Kershaw
 Author-email: dk107dk@hotmail.com
@@ -34,6 +34,7 @@ Requires-Dist: metaphone (>=0.6,<0.7)
 Requires-Dist: mysqlclient (>=2.2.7,<3.0.0)
 Requires-Dist: openlineage-python (>=1.25.0,<2.0.0)
 Requires-Dist: opentelemetry-distro[otlp] (>=0.50b0,<0.51)
+Requires-Dist: pandas (>=2.2.2,<3.0.0) ; extra == "pandas"
 Requires-Dist: paramiko (>=3.5.0,<4.0.0)
 Requires-Dist: pdoc (>=15.0.1,<16.0.0)
 Requires-Dist: prompt-toolkit (>=3.0.50,<4.0.0)

{csvpath-0.0.559 → csvpath-0.0.561}/assets/config/jenkins-local-azure.ini

@@ -11,8 +11,8 @@ extensions = csvpath, csvpaths
 extensions = csv, tsv, dat, tab, psv, ssv
 
 [errors]
-csvpath = raise, collect, print
-csvpaths = raise, collect, print
+csvpath = print,fail,collect
+csvpaths = print,collect
 use_format = full
 pattern = {time}:{file}:{line}:{paths}:{instance}:{chain}:  {message}
 
@@ -46,7 +46,7 @@ allow_http_files = True
 allow_local_files = True
 
 [listeners]
-groups = 
+groups = default
 sqlite.result = from csvpath.managers.integrations.sqlite.sqlite_result_listener import SqliteResultListener
 sqlite.results = from csvpath.managers.integrations.sqlite.sqlite_results_listener import SqliteResultsListener
 default.file = from csvpath.managers.files.files_listener import FilesListener

{csvpath-0.0.559 → csvpath-0.0.561}/config/config.ini

@@ -17,15 +17,15 @@ use_format = full
 pattern = {time}:{file}:{line}:{paths}:{instance}:{chain}:  {message}
 
 [logging]
-csvpath = info
-csvpaths = info
+csvpath = debug
+csvpaths = debug
 log_file = logs/csvpath.log
 log_files_to_keep = 100
 log_file_size = 52428800
 handler = file
 
 [config]
-path = assets/config/config.ini
+path = config/config.ini
 allow_var_sub = True
 var_sub_source = env
 
@@ -104,7 +104,7 @@ port = SFTPPLUS_PORT
 admin_username = SFTPPLUS_ADMIN_USERNAME
 admin_password = SFTPPLUS_ADMIN_PASSWORD
 api_url = https://localhost:10020/json
-scripts_dir = 
+scripts_dir =
 execute_timeout = 300
 
 [ckan]
@@ -119,7 +119,7 @@ timeout = 5
 verify = False
 
 [slack]
-webhook_url = 
+webhook_url =
 
 [scripts]
 run_scripts = yes

csvpath-0.0.561/config/env.json

@@ -0,0 +1 @@
+{}

{csvpath-0.0.559 → csvpath-0.0.561}/csvpath/csvpaths.py

@@ -160,6 +160,7 @@ class CsvPaths(CsvPathsCoordinator, ErrorCollector):
         """ @private """
         self._config._assure_logs_path()
         self.logger = LogUtility.logger(self)
+        self.info_dump()
         """ @private """
         self._errors = []
         # coordinator attributes
@@ -200,9 +201,20 @@ class CsvPaths(CsvPathsCoordinator, ErrorCollector):
         """ @private """
 
         self.logger.info(
-            "Initialized CsvPaths: {self} in thread: {threading.currentThread()}"
+            f"Initialized CsvPaths: {self} in thread: {threading.current_thread()}"
         )
 
+    def info_dump(self) -> None:
+        self.logger.info(
+            "Initated logging on log path: %s",
+            self.config.get(section="logging", name="log_file"),
+        )
+        self.logger.info("Config file is at: %s", self.config.configpath)
+        intgs = self.config.get(section="listeners", name="groups")
+        self.logger.debug("Active integrations:")
+        for _ in intgs:
+            self.logger.debug("  - %s", _)
+
     def _set_managers(self) -> None:
         self.paths_manager = PathsManager(csvpaths=self)
         self.file_manager = FileManager(csvpaths=self)
@@ -670,6 +682,7 @@ class CsvPaths(CsvPathsCoordinator, ErrorCollector):
             filename=filename,
             file=file,
             run_uuid=run_uuid,
+            method="collect_paths",
         )
         #
         #
@@ -686,6 +699,7 @@ class CsvPaths(CsvPathsCoordinator, ErrorCollector):
                 run_time=self.current_run_time,
                 run_dir=crt,
                 run_uuid=run_uuid,
+                method="collect_paths",
             )
             # casting a broad net because if "raise" not in the error policy we
             # want to never fail during a run
@@ -813,7 +827,11 @@ class CsvPaths(CsvPathsCoordinator, ErrorCollector):
         # run starts here
         #
         self.run_metadata = self.results_manager.start_run(
-            run_dir=crt, pathsname=pathsname, filename=filename, run_uuid=run_uuid
+            run_dir=crt,
+            pathsname=pathsname,
+            filename=filename,
+            run_uuid=run_uuid,
+            method="fast_forward_paths",
         )
         #
         #
@@ -830,6 +848,7 @@ class CsvPaths(CsvPathsCoordinator, ErrorCollector):
                 run_time=self.current_run_time,
                 run_dir=crt,
                 run_uuid=run_uuid,
+                method="fast_forward_paths",
             )
             try:
                 self._load_csvpath(
@@ -923,7 +942,11 @@ class CsvPaths(CsvPathsCoordinator, ErrorCollector):
         # run starts here
         #
         self.run_metadata = self.results_manager.start_run(
-            run_dir=crt, pathsname=pathsname, filename=filename, run_uuid=run_uuid
+            run_dir=crt,
+            pathsname=pathsname,
+            filename=filename,
+            run_uuid=run_uuid,
+            method="next_paths",
         )
         #
         #
@@ -956,6 +979,7 @@ class CsvPaths(CsvPathsCoordinator, ErrorCollector):
                 run_time=self.current_run_time,
                 run_dir=crt,
                 run_uuid=run_uuid,
+                method="next_paths",
             )
             if self._fail_all:
                 self.logger.warning(
@@ -1043,6 +1067,7 @@ class CsvPaths(CsvPathsCoordinator, ErrorCollector):
                 collect_when_not_matched=collect_when_not_matched,
                 file=file,
                 template=template,
+                method="collect_by_line",
             ):
                 # re: W0612: we need 'line' in order to do the iteration. we have to iterate.
                 lines.append(line)
@@ -1091,6 +1116,7 @@ class CsvPaths(CsvPathsCoordinator, ErrorCollector):
                 collect_when_not_matched=collect_when_not_matched,
                 file=file,
                 template=template,
+                method="fast_forward_by_line",
             ):
                 # re: W0612: we need 'line' in order to do the iteration. we have to iterate.
                 pass
@@ -1117,6 +1143,7 @@ class CsvPaths(CsvPathsCoordinator, ErrorCollector):
         if_all_agree=False,
         collect_when_not_matched=False,
         template: str = None,
+        method: str = None,
     ) -> List[Any]:
         #
         # we're doing a programmatic use when we use next_by_line() so we don't allow
@@ -1147,6 +1174,7 @@ class CsvPaths(CsvPathsCoordinator, ErrorCollector):
         collect_when_not_matched=False,
         template: str = None,
         file: str,
+        method: str = "next_by_line",
     ) -> List[Any]:
         """Does a CsvPath.next() on filename where each row is considered
         by every named path before the next row starts.
@@ -1200,6 +1228,7 @@ class CsvPaths(CsvPathsCoordinator, ErrorCollector):
             filename=filename,
             pathsname=pathsname,
             crt=crt,
+            method=method,
         )
         #
         # setting file into the csvpath is less obviously useful at CsvPaths
@@ -1370,7 +1399,9 @@ class CsvPaths(CsvPathsCoordinator, ErrorCollector):
                 self.error_manager.handle_error(source=self, msg=f"{ex}")
         return csvpath_objects
 
-    def _prep_csvpath_results(self, *, csvpath_objects, filename, pathsname, crt: str):
+    def _prep_csvpath_results(
+        self, *, csvpath_objects, filename, pathsname, crt: str, method: str
+    ):
         """@private"""
         #
         #
@@ -1380,7 +1411,11 @@ class CsvPaths(CsvPathsCoordinator, ErrorCollector):
         # run starts here
         #
         self.run_metadata = self.results_manager.start_run(
-            run_dir=crt, pathsname=pathsname, filename=filename, run_uuid=run_uuid
+            run_dir=crt,
+            pathsname=pathsname,
+            filename=filename,
+            run_uuid=run_uuid,
+            method="next_paths",
         )
         #
         #
@@ -1400,6 +1435,7 @@ class CsvPaths(CsvPathsCoordinator, ErrorCollector):
                     run_dir=crt,
                     by_line=True,
                     run_uuid=run_uuid,
+                    method=method,
                 )
                 csvpath[1] = result
                 #

{csvpath-0.0.559 → csvpath-0.0.561}/csvpath/managers/integrations/otlp/metrics.py

@@ -64,39 +64,57 @@ class Metrics:
     @property
     def provider(self) -> LoggerProvider:
         if self._provider is None:
-            # Add resource information
-            resource = Resource.create(
-                {"service.name": "CsvPath", "service.version": "1.0.0"}
-            )
-            self._provider = LoggerProvider(resource=resource)
-            set_logger_provider(self._provider)
-            #
-            # these were working values for openobserve. I don't think we need
-            # OTEL_EXPORTER_OTLP_PROTOCOL  since we are programmatically instantiating
-            # the protobuf
-            #
-            # OTEL_EXPORTER_OTLP_PROTOCOL=http/protobuf
-            # OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:5080/api/default
-            # OTEL_EXPORTER_OTLP_HEADERS=Authorization=Basic ZGsxMDdka0Bob3RtYWlsLmNvbTpoYW5nemhvdQ==,stream-name=FlightPath
-            #
-            # certificate_file=None,
-            # client_key_file=None,
-            # client_certificate_file=None,
-            # timeout=None,
-            # compression=None,
-            # session=None
-            #
-            # in CsvPath and FlightPath Data these can come from regular env vars
-            # but in FlightPath Server they must come from var_sub_source=config/env.json
-            # because we plan to allow projects to push data to their own choice of OTLP
-            # platform. FlightPath Data will have to provide an API for setting env.json
-            # and assistence in copying its own env vars and the OS env vars to env.json
-            # on the server.
-            #
-            endpoint = self._get(name="OTEL_EXPORTER_OTLP_ENDPOINT")
-            headers = self._get(name="OTEL_EXPORTER_OTLP_HEADERS")
-            exporter = OTLPLogExporter(endpoint=endpoint, headers=headers)
-            self._provider.add_log_record_processor(BatchLogRecordProcessor(exporter))
+            try:
+                # Add resource information
+                resource = Resource.create(
+                    {"service.name": "CsvPath", "service.version": "1.0.0"}
+                )
+                self._provider = LoggerProvider(resource=resource)
+                set_logger_provider(self._provider)
+                #
+                # these were working values for a local openobserve.
+                #
+                # OTEL_EXPORTER_OTLP_ENDPOINT=http://0.0.0.0:5080/api/default/v1/logs
+                # OTEL_EXPORTER_OTLP_HEADERS=Authorization=Basic ZGsxMDdka0Bob3RtYWlsLmNvbTpoYW5nemhvdQ==,stream-name=flightpath
+                #
+                # certificate_file=None,
+                # client_key_file=None,
+                # client_certificate_file=None,
+                # timeout=None,
+                # compression=None,
+                # session=None
+                #
+                # in CsvPath and FlightPath Data these can come from regular env vars
+                # but in FlightPath Server they must come from var_sub_source=config/env.json
+                # because we plan to allow projects to push data to their own choice of OTLP
+                # platform. FlightPath Data will have to provide an API for setting env.json
+                # and assistence in copying its own env vars and the OS env vars to env.json
+                # on the server.
+                #
+                endpoint = self._get(name="OTEL_EXPORTER_OTLP_LOGS_ENDPOINT")
+                if endpoint is None or endpoint == "OTEL_EXPORTER_OTLP_LOGS_ENDPOINT":
+                    endpoint = self._get(name="OTEL_EXPORTER_OTLP_ENDPOINT")
+                if endpoint is None or endpoint == "OTEL_EXPORTER_OTLP_ENDPOINT":
+                    raise ValueError(
+                        "You must pass either OTEL_EXPORTER_OTLP_ENDPOINT or OTEL_EXPORTER_OTLP_LOGS_ENDPOINT, the latter preferred"
+                    )
+                headers = self._get(name="OTEL_EXPORTER_OTLP_HEADERS")
+                if headers is None or headers == "OTEL_EXPORTER_OTLP_HEADERS":
+                    raise ValueError("OTEL_EXPORTER_OTLP_HEADERS cannot be None")
+                headers = headers.split(",")
+                d = {}
+                for _ in headers:
+                    k = _[0 : _.find("=")]
+                    v = _[_.find("=") + 1 :]
+                    d[k] = v
+                exporter = OTLPLogExporter(endpoint=endpoint, headers=d)
+                self._provider.add_log_record_processor(
+                    BatchLogRecordProcessor(exporter)
+                )
+            except Exception as ex:
+                if self._csvpaths:
+                    self._csvpaths.logger.error("Cannot configure OTLP")
+                    self._csvpaths.logger.error(ex)
         return self._provider
 
     def logger(self, project: str = "csvpath") -> Logger:
@@ -114,4 +132,5 @@ class Metrics:
             # Prevent propagation to avoid duplicate logs
             logger.propagate = False
             Metrics.LOGGERS[project] = logger
+            # logging.basicConfig(level=logging.DEBUG)
         return logger

{csvpath-0.0.559 → csvpath-0.0.561}/csvpath/managers/integrations/otlp/otlp_paths_listener.py

@@ -21,6 +21,13 @@ class OpenTelemetryPathsListener(OtlpListener):
             )
         self.assure_metrics()
         try:
+            ids = []
+            #
+            # otlp doesn't like Nones. should there not be any?
+            #
+            for _ in mdata.named_paths_identities:
+                if _:
+                    ids.append(_)
             etype = "named-paths group load"
             extra = {
                 "event_type": etype,
@@ -29,7 +36,7 @@ class OpenTelemetryPathsListener(OtlpListener):
                 "named_paths_home": mdata.named_paths_home,
                 "group_file_path": mdata.group_file_path,
                 "named_paths_count": mdata.named_paths_count,
-                "named_paths_identities": mdata.named_paths_identities,
+                "named_paths_identities": ids,
                 "source_path": mdata.source_path,
                 "template": mdata.template if mdata.template else "",
                 **self.core_meta(mdata),

{csvpath-0.0.559 → csvpath-0.0.561}/csvpath/managers/integrations/otlp/otlp_results_listener.py

@@ -49,6 +49,7 @@ class OpenTelemetryResultsListener(OtlpListener):
             self.csvpaths.__class__.METRICS.logger().debug(
                 "Csvpath completed", extra=extra
             )
+            self.csvpaths.logger.info("Csvpath shipped log entry to OTLP integration")
         except Exception as ex:
             print(traceback.format_exc())
             self.csvpaths.logger.error(ex)

{csvpath-0.0.559 → csvpath-0.0.561}/csvpath/managers/registrar.py

@@ -51,13 +51,18 @@ class Registrar(ABC):
         # notable exception of errors, errors are not thrown in non-CsvPaths code.
         #
         if self.csvpaths is not None:
+            self.csvpaths.logger.info("Distributing updates to listeners")
             try:
                 self.load_additional_listeners(self.type_name, listeners)
             except Exception as ex:
                 print(traceback.format_exc())
                 if self.csvpaths:
-                    self.csvpaths.logger(f"Error in loading listeners: {ex}")
+                    self.csvpaths.logger.error(f"Error in loading listeners: {ex}")
         for lst in listeners:
+            if self.csvpaths:
+                self.csvpaths.logger.debug(
+                    "Updating listener %s with metadata %s", lst, mdata
+                )
             try:
                 lst.metadata_update(mdata)
             except Exception as ex:
@@ -75,27 +80,27 @@ class Registrar(ABC):
         """
         if self.csvpaths:
             ss = self.csvpaths.config.additional_listeners(listener_type_name)
+            self.csvpaths.logger.info("Loading additional listener type(s) %s", ss)
             if ss and not isinstance(ss, list):
                 ss = [ss]
             if ss and len(ss) > 0:
                 for lst in ss:
-                    try:
-                        self.load_additional_listener(lst, listeners)
-                    except Exception as ex:
-                        print(traceback.format_exc())
-                        self.csvpaths.logger.error(
-                            f"Failed to load listener {lst}: {ex}"
-                        )
+                    self.load_additional_listener(lst, listeners)
 
     def load_additional_listener(self, load_cmd: str, listeners: list) -> None:
-        loader = ClassLoader()
-        alistener = loader.load(load_cmd)
-        if alistener is not None:
-            if hasattr(alistener, "csvpaths"):
-                setattr(alistener, "csvpaths", self.csvpaths)
-            if hasattr(alistener, "result"):
-                setattr(alistener, "result", self.result)
-            if hasattr(self, "csvpath") and hasattr(alistener, "csvpath"):
-                alistener.csvpath = self.csvpath
-            alistener.config = self.csvpaths.config
-            listeners.append(alistener)
+        self.csvpaths.logger.info("Loading additional listener %s", load_cmd)
+        try:
+            loader = ClassLoader()
+            alistener = loader.load(load_cmd)
+            if alistener is not None:
+                if hasattr(alistener, "csvpaths"):
+                    setattr(alistener, "csvpaths", self.csvpaths)
+                if hasattr(alistener, "result"):
+                    setattr(alistener, "result", self.result)
+                if hasattr(self, "csvpath") and hasattr(alistener, "csvpath"):
+                    alistener.csvpath = self.csvpath
+                alistener.config = self.csvpaths.config
+                listeners.append(alistener)
+        except Exception as e:
+            print(traceback.format_exc())
+            self.csvpaths.logger.error(e)

{csvpath-0.0.559 → csvpath-0.0.561}/csvpath/managers/results/result.py

@@ -39,6 +39,7 @@ class Result(ErrorCollector, Printer, Listener):  # pylint: disable=R0902
         runtime_data: dict = None,
         by_line: bool = False,
         run_uuid: UUID,
+        method: str = None,
     ):
         """@private"""
         ErrorCollector.__init__(self)
@@ -63,6 +64,7 @@ class Result(ErrorCollector, Printer, Listener):  # pylint: disable=R0902
         self._actual_data_file = None
         self._origin_data_file = None
         self._by_line = by_line
+        self._method = method
         #
         # data_file_path is the path to data.csv of this result
         #
@@ -167,6 +169,10 @@ class Result(ErrorCollector, Printer, Listener):  # pylint: disable=R0902
     def by_line(self) -> bool:
         return self._by_line
 
+    @property
+    def method(self) -> bool:
+        return self._method
+
     @property
     def source_mode_preceding(self) -> bool:
         if self._preceding is None:

{csvpath-0.0.559 → csvpath-0.0.561}/csvpath/managers/results/result_metadata.py

@@ -58,10 +58,8 @@ class ResultMetadata(Metadata):
         self.lines_scanned: int = 0
         self.lines_total: int = 0
         self.lines_matched: int = 0
-        #
-        # why do we need this here? the run knows.
-        #
         self.by_line: bool = False
+        self.method: str = None
         #
         # transfer tuples:
         # 1: filename, no extension needed: data | unmatched
@@ -79,6 +77,7 @@ ResultMetadata(
   {self.run_home},{self.instance_home},
   {self.input_data_file},
   {self.file_fingerprints},
+  {self.method},
   {self.valid},{self.completed},{self.files_expected},{self.error_count},
   {self.transfers}
 )"""  # {self.file_count},
@@ -98,6 +97,7 @@ ResultMetadata(
         #
         #
         self.run = m.get("run")
+        self.method = m.get("method")
         self.run_uuid_string = m.get("run_uuid")
         self.run_home = m.get("run_home")
         self.instance_home = m.get("instance_home")

{csvpath-0.0.559 → csvpath-0.0.561}/csvpath/managers/results/results_manager.py

@@ -88,7 +88,14 @@ class ResultsManager:  # pylint: disable=C0115
     # and return that uuid.
     #
     def start_run(
-        self, *, run_dir, pathsname, filename, file: str = None, run_uuid: UUID
+        self,
+        *,
+        run_dir: str,
+        pathsname: str,
+        filename: str,
+        file: str = None,
+        run_uuid: UUID,
+        method: str,
     ) -> ResultsMetadata:
         """@private"""
         rr = ResultsRegistrar(
@@ -121,6 +128,7 @@ class ResultsManager:  # pylint: disable=C0115
         mdata.named_paths_name = pathsname
         mdata.named_paths_uuid_string = np_uuid
         mdata.named_results_name = pathsname
+        mdata.method = method
         rr.register_start(mdata)
         return mdata
 
@@ -323,6 +331,7 @@ class ResultsManager:  # pylint: disable=C0115
         mdata.identity = result.identity_or_index
         mdata.named_paths_name = result.paths_name
         mdata.named_file_name = result.file_name
+        mdata.method = result.method
         rr = RunRegistrar(self.csvpaths)
         rr.register_start(mdata)
         #
@@ -331,6 +340,10 @@ class ResultsManager:  # pylint: disable=C0115
         # we use the same UUID for both metadata updates because the
         # UUID represents the run, not the metadata object
         #
+        #
+        # collect_paths and collect_by_line expect a data.csv file, even if it has 0-bytes.
+        # we make sure of that here.
+        #
         mdata = ResultMetadata(self.csvpaths.config)
         mdata.uuid = result.uuid
         mdata.run_uuid = result.run_uuid
@@ -341,6 +354,18 @@ class ResultsManager:  # pylint: disable=C0115
         mdata.run = result.run_dir[result.run_dir.rfind(sep) + 1 :]
         mdata.run_home = result.run_dir
         mdata.instance_home = result.instance_dir
+        mdata.method = result.method
+        #
+        # for the two CsvPaths methods that result in data.csv we want to make
+        # sure there is a data.csv, even if it ends up empty. we don't make this
+        # effort for unmatched.csv. perhaps we should but atm seems ok to pass.
+        #
+        if mdata.method in ["collect_paths", "collect_by_line"]:
+            path = Nos(mdata.instance_home).join("data.csv")
+            nos = Nos(path)
+            if not nos.exists():
+                with DataFileWriter(path=path) as file:
+                    file.write("")
         mdata.instance_identity = result.identity_or_index
         mdata.input_data_file = result.file_name
         rs = ResultSerializer(self._csvpaths.config.archive_path)

{csvpath-0.0.559 → csvpath-0.0.561}/csvpath/managers/results/results_metadata.py

@@ -26,6 +26,15 @@ class ResultsMetadata(Metadata):
         self.all_expected_files: bool = None
         self.by_line: bool = False
         self._run_uuid: UUID = None
+        self._method: str = None
+
+    @property
+    def method(self) -> str:
+        return self._method
+
+    @method.setter
+    def method(self, m: str) -> None:
+        self._method = m
 
     @property
     def run_uuid(self) -> UUID:
@@ -101,3 +110,4 @@ class ResultsMetadata(Metadata):
         self.all_valid = m.get("all_valid")
         self.error_count = m.get("error_count")
         self.all_expected_files = m.get("all_expected_files")
+        self.method = m.get("method")

{csvpath-0.0.559 → csvpath-0.0.561}/csvpath/managers/results/results_registrar.py

@@ -122,6 +122,7 @@ class ResultsRegistrar(Registrar, Listener):
         m["hostname"] = mdata.hostname
         m["username"] = mdata.username
         m["ip_address"] = mdata.ip_address
+        m["method"] = mdata.method
         mp = mdata.manifest_path
         m["manifest_path"] = mp
         with DataFileWriter(path=mp) as file:

{csvpath-0.0.559 → csvpath-0.0.561}/csvpath/managers/run/run_metadata.py

@@ -11,6 +11,7 @@ class RunMetadata(Metadata):
         self.named_file_name: str = None
         self.identity: str = None
         self._run_uuid: UUID = None
+        self._method: str = None
 
     @property
     def run_uuid(self) -> UUID:
@@ -29,3 +30,11 @@ class RunMetadata(Metadata):
     @run_uuid_string.setter
     def run_uuid_string(self, u: str) -> None:
         self._run_uuid = UUID(u)
+
+    @property
+    def method(self) -> str:
+        return self._method
+
+    @method.setter
+    def method(self, m: str) -> None:
+        self._method = m

{csvpath-0.0.559 → csvpath-0.0.561}/csvpath/matching/functions/validity/line.py

@@ -248,7 +248,8 @@ class Line(MatchDecider):
         #
         if t and t.name != self.matcher.csvpath.headers[i] and t.name != f"{i}":
             ii = i + 1
-            msg = f"The {ExpressionUtility._numeric_string(ii)} item, {t}, does not match the current header"
+
+            msg = f"The {ExpressionUtility._numeric_string(ii)} item, {t}, does not match the current header '{self.matcher.csvpath.headers[i]}'"
             errors.append(msg)
         return True
 
@@ -264,6 +265,6 @@ class Line(MatchDecider):
         #
         if t and t.name != self.matcher.csvpath.headers[i] and t.name != f"{i}":
             ii = i + 1
-            msg = f"The {ExpressionUtility._numeric_string(ii)} item, {t}, does not match the current header"
+            msg = f"The {ExpressionUtility._numeric_string(ii)} item, {t}, does not match the current header '{self.matcher.csvpath.headers[i]}'"
             errors.append(msg)
         return True

{csvpath-0.0.559 → csvpath-0.0.561}/csvpath/matching/productions/reference.py

@@ -198,7 +198,7 @@ class Reference(Matchable):
             else:
                 ret = v
         else:
-            msg = f"Results exist but the {ref['name']} variable is unknown: {self.my_chain}"
+            msg = f"The {ref['name']} variable is unknown: {self.my_chain}"
             self.matcher.csvpath.error_manager.handle_error(source=self, msg=msg)
             if self.matcher.csvpath.do_i_raise():
                 raise DataException(msg)