Merge pull request #103 from codereverser/feature/cdsl-ndsl-parser

NSDL support: alpha version

Author: codereverser

.github/workflows/pypi-publish.yml

@@ -7,20 +7,19 @@ on:
 jobs:
   deploy:
     environment: pypi
+    permissions:
+      id-token: write
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v3
-    - name: Install poetry
-      run: pipx install poetry
+    - uses: actions/checkout@v4
     - name: Set up Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
-        python-version: '3.8'
-    - name: Build and publish
-      env:
-        PYPI_TOKEN: ${{ secrets.PYPI_PASSWORD }}
-      run: |
-        poetry self add poetry-version-plugin
-        poetry config pypi-token.pypi $PYPI_TOKEN
-        poetry publish --build
+        python-version: '3.10'
+    - name: Install uv
+      uses: astral-sh/setup-uv@v5
+    - name: Build
+      run: uv build
+    - name: Publish
+      run: uv publish

.github/workflows/run-pytest.yml

@@ -2,6 +2,10 @@ name: run-tests
 
 on:
   push:
+    branches:
+      - '*'
+    tags-ignore:
+      - 'v*'
   pull_request:
     branches:
       - main
@@ -14,22 +18,21 @@ jobs:
         python-version: ['3.10']
 
     steps:
-    - uses: actions/checkout@v3
-    - name: Install poetry
-      run: pipx install poetry
+    - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
-        cache: 'poetry'
+    - name: Install uv
+      uses: astral-sh/setup-uv@v5
+    - name: Install dependencies
+      run: uv sync --all-extras --dev
     - name: Extract test files
       run: ./.github/scripts/extract_files.sh
       env:
         FILES_PASSPHRASE: ${{ secrets.FILES_PASSPHRASE }}
-    - name: Install dependencies
-      run: poetry install -E mupdf
     - name: Test with pytest
-      run: poetry run pytest
+      run: uv run pytest
       env:
         BAD_CAS_FILE: ${{ secrets.BAD_CAS_FILE }}
         CAMS_CAS_FILE: ${{ secrets.CAMS_CAS_FILE }}
@@ -40,6 +43,7 @@ jobs:
         KFINTECH_CAS_FILE: ${{ secrets.KFINTECH_CAS_FILE }}
         KFINTECH_CAS_FILE_NEW: ${{ secrets.KFINTECH_CAS_FILE_NEW }}
         KFINTECH_CAS_PASSWORD: ${{ secrets.KFINTECH_CAS_PASSWORD }}
+        NSDL_CAS_FILE_1: ${{ secrets.NSDL_CAS_FILE_1 }}
     - name: Upload coverage report to codecov
       uses: codecov/codecov-action@v5
       with:

casparser/__init__.py

@@ -9,4 +9,4 @@
     "CapitalGainsReport",
 ]
 
-__version__ = "0.7.4"
+__version__ = "0.8.0"

casparser/cli.py

@@ -15,10 +15,10 @@
 
 from . import __version__, read_cas_pdf
 from .analysis.gains import CapitalGainsReport
-from .enums import CASFileType
+from .enums import CASFileType, FileType
 from .exceptions import GainsError, IncompleteCASError, ParserException
 from .parsers.utils import cas2csv, cas2csv_summary, cas2json, is_close
-from .types import CASData
+from .types import CASData, NSDLCASData
 
 CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"])
 console = Console()
@@ -55,6 +55,99 @@ def get_color(amount: Union[Decimal, float, int]):
     return "white"
 
 
+def print_nsdl(parsed_data: NSDLCASData):
+    """Print summary of parsed data."""
+
+    count = 0
+    err = 0
+
+    data = parsed_data.model_dump(by_alias=True)
+    # console.print(data)
+
+    summary_table = Table.grid(expand=True)
+    summary_table.add_column(justify="right")
+    summary_table.add_column(justify="left")
+    spacing = (0, 1)
+    summary_table.add_row(
+        Padding("Statement Period :", spacing),
+        f"[bold green]{data['statement_period']['from']}[/] To "
+        f"[bold green]{data['statement_period']['to']}[/]",
+    )
+    summary_table.add_row(Padding("File Type :", spacing), f"[bold]{data['file_type']}[/]")
+    # summary_table.add_row(Padding("CAS Type :", spacing), f"[bold]{data['cas_type']}[/]")
+    for key, value in data["investor_info"].items():
+        summary_table.add_row(
+            Padding(f"{key.capitalize()} :", spacing), re.sub(r"[^\S\r\n]+", " ", value)
+        )
+    console.print(summary_table)
+    console.print("")
+
+    table = Table(title="Portfolio Summary", show_lines=True)
+    table.add_column("Name")
+    table.add_column("ISIN")
+    table.add_column("Units")
+    table.add_column("Price")
+    table.add_column("Value")
+
+    value = Decimal(0)
+
+    for account in parsed_data.accounts:
+        balance = account.balance
+        value += balance
+        running_balance = 0
+        table_rows = []
+        if len(account.equities) > 0:
+            table_rows.append(["[italic]Equities[/]"])
+        for equity in account.equities:
+            running_balance += equity.num_shares * equity.price
+            table_rows.append(
+                [
+                    equity.name,
+                    equity.isin,
+                    format_number(equity.num_shares),
+                    formatINR(equity.price),
+                    formatINR(equity.value),
+                ]
+            )
+        if len(account.mutual_funds) > 0:
+            table_rows.append(["[italic]Mutual Funds[/]"])
+        for mf in account.mutual_funds:
+            running_balance += mf.nav * mf.balance
+            table_rows.append(
+                [
+                    mf.name,
+                    mf.isin,
+                    format_number(mf.balance),
+                    formatINR(mf.nav),
+                    formatINR(mf.value),
+                ]
+            )
+        if is_close(balance, running_balance, tol=float(balance or 1) * 0.01):
+            status = "️✅"
+        else:
+            status = "❗️"
+            err += 1
+        count += 1
+        table.add_row(
+            f"[bold]{account.name}\n{account.dp_id} - {account.client_id}[/]", "", "", "", status
+        )
+
+        for row in table_rows:
+            table.add_row(*row)
+
+    console.print(table)
+
+    console.print(
+        f"Portfolio Valuation  : [bold green]{formatINR(value)}[/] "
+        f"[As of {data['statement_period']['to']}]"
+    )
+
+    console.print("[bold]Summary[/]")
+    console.print(f"{'Total':8s}: [bold white]{count:4d}[/] accounts")
+    console.print(f"{'Matched':8s}: [bold green]{count - err:4d}[/] accounts")
+    console.print(f"{'Error':8s}: [bold red]{err:4d}[/] accounts")
+
+
 def print_summary(parsed_data: CASData, output_filename=None, include_zero_folios=False):
     """Print summary of parsed data."""
     count = 0
@@ -348,15 +441,20 @@ def cli(output, summary, password, include_all, gains, gains_112a, force_pdfmine
     except ParserException as exc:
         console.print(f"Error parsing pdf file :: [bold red]{str(exc)}[/]")
         sys.exit(1)
-    if summary:
+    if isinstance(data, NSDLCASData):
+        print_nsdl(data)
+    elif summary:
         print_summary(
             data,
             include_zero_folios=include_all,
             output_filename=None if output_ext in (".csv", ".json") else output,
         )
 
     if output_ext in (".csv", ".json"):
-        if output_ext == ".csv":
+        if output_ext == ".csv" and data.file_type in (
+            FileType.CAMS.value,
+            FileType.KFINTECH.value,
+        ):
             if summary or data.cas_type == CASFileType.SUMMARY.name:
                 description = "Generating summary CSV file..."
                 conv_fn = cas2csv_summary
@@ -370,7 +468,7 @@ def cli(output, summary, password, include_all, gains, gains_112a, force_pdfmine
         with open(output, "w", newline="", encoding="utf-8") as fp:
             fp.write(conv_fn(data))
         console.print(f"File saved : [bold]{output}[/]")
-    if gains or gains_112a:
+    if data.file_type in (FileType.CAMS.value, FileType.KFINTECH.value) and (gains or gains_112a):
         try:
             print_gains(
                 data,

casparser/enums.py

@@ -17,6 +17,8 @@ class FileType(AutoEnum):
     UNKNOWN = auto()
     CAMS = auto()
     KFINTECH = auto()
+    CDSL = auto()
+    NSDL = auto()
 
 
 class CASFileType(AutoEnum):

casparser/parsers/__init__.py

@@ -2,7 +2,7 @@
 from typing import Union
 
 from casparser.process import process_cas_text
-from casparser.types import CASData
+from casparser.types import CASData, NSDLCASData, ProcessedCASData
 
 from .utils import cas2csv, cas2json
 
@@ -32,31 +32,39 @@ def read_cas_pdf(
             from .pdfminer import cas_pdf_to_text
 
     partial_cas_data = cas_pdf_to_text(filename, password)
-
-    processed_data = process_cas_text("\u2029".join(partial_cas_data.lines))
-
-    if sort_transactions:
-        for folio in processed_data.folios:
-            for idx, scheme in enumerate(folio.schemes):
-                dates = [x.date for x in scheme.transactions]
-                sorted_dates = list(sorted(dates))
-                if dates != sorted_dates:
-                    sorted_transactions = []
-                    balance = scheme.open
-                    for transaction in sorted(scheme.transactions, key=lambda x: x.date):
-                        balance += transaction.units or 0
-                        transaction.balance = balance
-                        sorted_transactions.append(transaction)
-                    scheme.transactions = sorted_transactions
-                folio.schemes[idx] = scheme
-
-    final_data = CASData(
-        statement_period=processed_data.statement_period,
-        folios=processed_data.folios,
-        investor_info=partial_cas_data.investor_info,
-        cas_type=processed_data.cas_type,
-        file_type=partial_cas_data.file_type,
+    processed_data = process_cas_text(
+        "\u2029".join(partial_cas_data.lines), partial_cas_data.file_type
     )
+    if isinstance(processed_data, ProcessedCASData):
+        if sort_transactions:
+            for folio in processed_data.folios:
+                for idx, scheme in enumerate(folio.schemes):
+                    dates = [x.date for x in scheme.transactions]
+                    sorted_dates = list(sorted(dates))
+                    if dates != sorted_dates:
+                        sorted_transactions = []
+                        balance = scheme.open
+                        for transaction in sorted(scheme.transactions, key=lambda x: x.date):
+                            balance += transaction.units or 0
+                            transaction.balance = balance
+                            sorted_transactions.append(transaction)
+                        scheme.transactions = sorted_transactions
+                    folio.schemes[idx] = scheme
+
+        final_data = CASData(
+            statement_period=processed_data.statement_period,
+            folios=processed_data.folios,
+            investor_info=partial_cas_data.investor_info,
+            cas_type=processed_data.cas_type,
+            file_type=partial_cas_data.file_type,
+        )
+    else:
+        final_data = NSDLCASData(
+            statement_period=processed_data.statement_period,
+            accounts=processed_data.accounts,
+            investor_info=partial_cas_data.investor_info,
+            file_type=partial_cas_data.file_type,
+        )
     if output == "dict":
         return final_data
     elif output == "csv":