Save spreadsheets in JSON format

Author: istride

src/rpft/converters.py

@@ -5,6 +5,7 @@
 from rpft.parsers.creation.contentindexparser import ContentIndexParser
 from rpft.parsers.creation.tagmatcher import TagMatcher
 from rpft.parsers.sheets import (
+    AbstractSheetReader,
     CSVSheetReader,
     GoogleSheetReader,
     XLSXSheetReader,
@@ -73,6 +74,20 @@ def sheet_to_csv(path, sheet_id):
             csv_file.write(sheet.table.export("csv"))
 
 
+def to_json(reader: AbstractSheetReader) -> str:
+    book = {
+        "meta": {
+            "version": "0.1.0",
+        },
+        "sheets": {
+            name: sheet.table.dict
+            for name, sheet in reader.sheets.items()
+        },
+    }
+
+    return json.dumps(book, ensure_ascii=False, indent=2, sort_keys=True)
+
+
 def prepare_dir(path):
     directory = Path(path)
 

src/rpft/parsers/sheets.py

@@ -1,6 +1,7 @@
 import json
 import os
 from abc import ABC
+from collections.abc import Mapping
 from pathlib import Path
 from typing import List
 
@@ -24,6 +25,10 @@ def __init__(self, reader, name, table):
 
 
 class AbstractSheetReader(ABC):
+    @property
+    def sheets(self) -> Mapping[str, Sheet]:
+        return self._sheets
+
     def get_sheet(self, name) -> Sheet:
         return self.sheets.get(name)
 
@@ -34,7 +39,7 @@ def get_sheets_by_name(self, name) -> List[Sheet]:
 class CSVSheetReader(AbstractSheetReader):
     def __init__(self, path):
         self.name = path
-        self.sheets = {
+        self._sheets = {
             f.stem: Sheet(reader=self, name=f.stem, table=load_csv(f))
             for f in Path(path).glob("*.csv")
         }
@@ -45,7 +50,7 @@ def __init__(self, filename):
         self.name = filename
         with open(filename, "rb") as table_data:
             data = tablib.Databook().load(table_data.read(), "xlsx")
-        self.sheets = {}
+        self._sheets = {}
         for sheet in data.sheets():
             self.sheets[sheet.title] = Sheet(
                 reader=self,
@@ -98,16 +103,16 @@ def __init__(self, spreadsheet_id):
             .execute()
         )
 
-        self.sheets = {}
+        self._sheets = {}
         for sheet in result.get("valueRanges", []):
             name = sheet.get("range", "").split("!")[0]
             if name.startswith("'") and name.endswith("'"):
                 name = name[1:-1]
             content = sheet.get("values", [])
-            if name in self.sheets:
+            if name in self._sheets:
                 raise ValueError(f"Warning: Duplicate sheet name: {name}")
             else:
-                self.sheets[name] = Sheet(
+                self._sheets[name] = Sheet(
                     reader=self,
                     name=name,
                     table=self._table_from_content(content),

tests/mocks.py

@@ -52,17 +52,17 @@ def parse_next_row(self, omit_templating=False, return_index=False):
 class MockSheetReader(AbstractSheetReader):
     def __init__(self, main_sheet_data=None, sheet_data_dict={}, name="mock"):
         self.name = name
-        self.sheets = {}
+        self._sheets = {}
 
         if main_sheet_data:
-            self.sheets["content_index"] = Sheet(
+            self._sheets["content_index"] = Sheet(
                 reader=self,
                 name="content_index",
                 table=tablib.import_set(main_sheet_data, format="csv"),
             )
 
         for name, content in sheet_data_dict.items():
-            self.sheets[name] = Sheet(
+            self._sheets[name] = Sheet(
                 reader=self,
                 name=name,
                 table=tablib.import_set(content, format="csv"),

tests/test_converters.py

@@ -0,0 +1,60 @@
+import json
+from unittest import TestCase
+
+from tablib import Dataset
+
+from rpft.converters import to_json
+from rpft.parsers.sheets import AbstractSheetReader, Sheet
+
+
+class TestReaderToJson(TestCase):
+    def test_something(self):
+        reader = MockSheetReader(
+            {
+                "sheet1": Sheet(
+                    reader=None,
+                    name="sheet1",
+                    table=Dataset(
+                        ("row1_col1", "row1_col2", "row1_col3"),
+                        headers=["col1", "col2", "col3"],
+                    ),
+                ),
+                "sheet2": Sheet(
+                    reader=None,
+                    name="sheet2",
+                    table=Dataset(
+                        ("row1_col1", "row1_col2", "row1_col3"),
+                        headers=["col1", "col2", "col3"],
+                    ),
+                ),
+            }
+        )
+        self.assertDictEqual(
+            json.loads(to_json(reader)),
+            {
+                "meta": {
+                    "version": "0.1.0",
+                },
+                "sheets": {
+                    "sheet1": [
+                        {
+                            "col1": "row1_col1",
+                            "col2": "row1_col2",
+                            "col3": "row1_col3",
+                        },
+                    ],
+                    "sheet2": [
+                        {
+                            "col1": "row1_col1",
+                            "col2": "row1_col2",
+                            "col3": "row1_col3",
+                        },
+                    ],
+                },
+            },
+        )
+
+
+class MockSheetReader(AbstractSheetReader):
+    def __init__(self, sheets):
+        self._sheets = sheets