bug fixes and functionality from issue #2

Author: Jesse

.gitignore

@@ -3,6 +3,7 @@
 *.csv
 *.xlsx
 temp/
+test.py
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

CHANGELOG.md

@@ -1,5 +1,16 @@
 # Changelog - xer-reader
 
+## 0.4.0 - 2024-11-21
+
+* Reference [Issue #2](https://github.com/jjCode01/xer-reader/issues/2)
+    * The `to_dict` method no longer throws an error if an unreckognized table is found; it now just ignores the table.
+    * Added `FINTMPL` to table_data.
+    * Updated `to_csv` method:
+        * Can now pass a list of table names to export to CSV. For example pass in agrument `table_names=["TASK", "PROJWBS"]` to only export the task and wbs tables to CSV.  
+        * Can now change the delimeter. For example, pass in argument `delimeter=","` to use a coma rather than the default tab.
+
+---  
+
 ## 0.3.2 - 2024-10-05  
 
 Clean up code.

README.md

@@ -74,9 +74,15 @@ Return True if table (`table_name`) if found in the XER file.
 **`parse_tables()`** -> *dict[str, Table]*  
 Returns a dictionary with the table name as the key and a `Table` object as the value.  
 
-**`to_csv(file_directory: str | Path)`** -> *None*  
-Generate a CSV file for each table in the XER file using 'tab' as the delimiter. CSV files will be created in the current working directory.   
-Optional: Pass a string or Path object (`file_directory`) to speficy a folder to store the CSV files in.  
+**`to_csv(file_directory: str | Path, table_names: list[str], delimeter: str)`** -> *None*  
+Generate a CSV file for each table in the XER file. CSV files will be created in the current working directory.   
+Optional `file_directory`: Pass a string or Path object to speficy a folder to store the CSV files in.  
+Optional `table_names`: List of tables names to save to CSV files.  
+Optional `delimeter`: Change the default delimeter from a `tab` to another string (e.g. a coma ",").  
+
+```python
+reader.to_csv(table_names=["TASK", "PROJWBS"], delimeter=",")
+```
 
 **`to_excel()`** -> *None*  
 Generate an Excel (.xlsx) file with each table in the XER file on its own spreadsheet. The Excel file will be create in the 

poetry.lock

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "xer-reader"
-version = "0.3.2"
+version = "0.4.0"
 description = "Read and parse a Primavera P6 xer file."
 authors = ["Jesse Jones <code@seqmanagement.com>"]
 license = "GPL-3.0-only"

pyproject.toml

@@ -75,25 +75,25 @@ def test_get_table_str(self):
             self.assertEqual(reader.get_table_str("PROJECT")[:7], "proj_id")
             self.assertEqual(reader.get_table_str("PROJWBS")[:6], "wbs_id")
 
-    # def test_to_csv(self):
-    #     print(f"Running to_csv tests on {len(self.files)} .xer files.")
-    #     for file in tqdm(self.files):
-    #         reader = XerReader(file)
-    #         tables = reader.to_dict()
-    #         temp_folder = Path.cwd().joinpath("temp")
-    #         if not temp_folder.is_dir():
-    #             Path.mkdir(temp_folder)
-
-    #         reader.to_csv(temp_folder)
-
-    #         for table_name in tables.keys():
-    #             csv_file = temp_folder.joinpath(f"{reader.file_name}_{table_name}.csv")
-    #             self.assertTrue(
-    #                 csv_file.is_file(),
-    #                 f"{table_name}.csv",
-    #             )
-    #             if csv_file.is_file():
-    #                 Path.unlink(csv_file)
+    def test_to_csv(self):
+        print(f"Running to_csv tests on {len(self.files)} .xer files.")
+        for file in tqdm(self.files):
+            reader = XerReader(file)
+            tables = reader.to_dict()
+            temp_folder = Path.cwd().joinpath("temp")
+            if not temp_folder.is_dir():
+                Path.mkdir(temp_folder)
+
+            reader.to_csv(temp_folder)
+
+            for table_name in tables.keys():
+                csv_file = temp_folder.joinpath(f"{reader.file_name}_{table_name}.csv")
+                self.assertTrue(
+                    csv_file.is_file(),
+                    f"{table_name}.csv",
+                )
+                if csv_file.is_file():
+                    Path.unlink(csv_file)
 
     # def test_to_excel(self):
     #     print(f"Running to_excel tests on {len(self.files)} .xer files.")

tests/test_reader.py

@@ -1,4 +1,4 @@
-__version__ = "0.3.2"
+__version__ = "0.4.0"
 
 from xer_reader.src.reader import XerReader  # noqa: F401
 from xer_reader.src.table import XerTable  # noqa: F401

xer_reader/__init__.py

@@ -14,7 +14,7 @@
 from openpyxl import Workbook
 from openpyxl.worksheet.table import Table
 
-from xer_reader.src.table import XerTable, UnrecognizedTable 
+from xer_reader.src.table import XerTable, UnrecognizedTable
 from xer_reader.src.table_data import table_data
 
 DATE_FORMAT = "%Y-%m-%d"
@@ -157,22 +157,32 @@ def to_dict(self) -> dict[str, XerTable]:
                 table = XerTable(table_str)
                 tables[table.name] = table
             except UnrecognizedTable:
-                continue 
+                continue
         return tables
 
-    def to_csv(self, file_directory: str | Path = Path.cwd(), tables: list[str] = []) -> None:
+    def to_csv(
+        self,
+        file_directory: str | Path = Path.cwd(),
+        table_names: list[str] = [],
+        delimeter: str = "\t",
+    ) -> None:
         """
         Generate a CSV file for each table in the XER file.
-        Uses `tab` as the delimiter.
+        Uses `tab` as the delimiter by default.
 
         Args:
-            file_directory (str | Path, optional): Directory to save CSV files.
-            Defaults to current working directory.
+            file_directory (str | Path, optional): Directory to save CSV files. [Defaults to current working directory]
+            table_names (list, optional): List of table names to save to CSV files. If empty, all tables will be saved.
+            delimeter (str, optional): CSV delimeter. [Default is a `tab`]
         """
-        for name, table in self.to_dict().entries():
-            if not tables or name in tables:
+        names = [name.upper() for name in table_names]
+        for table in self.to_dict().values():
+            if not table_names or table.name in names:
                 _write_table_to_csv(
-                    f"{self.file_name}_{table.name}", table, Path(file_directory)
+                    f"{self.file_name}_{table.name}",
+                    table,
+                    Path(file_directory),
+                    delimeter,
                 )
 
     def to_excel(self, file_directory: str | Path = Path.cwd()) -> None:
@@ -259,9 +269,11 @@ def _read_file(file: str | Path | BinaryIO) -> tuple[str, str]:
     return file_name, file_contents
 
 
-def _write_table_to_csv(name: str, table: XerTable, file_directory: Path) -> None:
+def _write_table_to_csv(
+    name: str, table: XerTable, file_directory: Path, delimeter
+) -> None:
     with file_directory.joinpath(f"{name}.csv").open("w") as f:
-        writer = csv.writer(f, delimiter="\t")
+        writer = csv.writer(f, delimiter=delimeter)
         writer.writerow(table.labels)
         for row in table.rows:
             writer.writerow(row)