pyxlsbwriter 0.0.1__tar.gz

pyxlsbwriter-0.0.1/PKG-INFO

@@ -0,0 +1,48 @@
+Metadata-Version: 2.4
+Name: pyxlsbwriter
+Version: 0.0.1
+Summary: A Python library to write XLSB files.
+Author: Krzysztof Duśko
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: xlsxwriter
+Provides-Extra: test
+Requires-Dist: pyodbc; extra == "test"
+Provides-Extra: examples
+Requires-Dist: memory-profiler; extra == "examples"
+
+# Python XLSB Writer
+
+A Python library for writing large data sets to XLSB files efficiently.
+
+## Installation
+
+```bash
+pip install pyxlsbwriter
+```
+
+## Usage
+
+```python
+from pyxlsbwriter import XlsbWriter
+import datetime
+from decimal import Decimal
+
+data = [
+    ["Name", "Age", "City", "info"],
+    [-123, 2147483647, 2147483648, 2147483999],
+    ["x", "y", "z", datetime.datetime.today()],
+    ["Alice", 25, "New York", datetime.date.today()],
+    ["Bob", 30, "London", Decimal(3.14)],
+    ["Charlie", 35, "Paris", datetime.datetime.now()],
+    [True, False, None, datetime.datetime.utcnow()]
+]
+
+writer = XlsbWriter("test.xlsb")
+writer.add_sheet("Sheet1")
+writer.write_sheet(data)
+writer.save()
+```

pyxlsbwriter-0.0.1/README.md

@@ -0,0 +1,32 @@
+# Python XLSB Writer
+
+A Python library for writing large data sets to XLSB files efficiently.
+
+## Installation
+
+```bash
+pip install pyxlsbwriter
+```
+
+## Usage
+
+```python
+from pyxlsbwriter import XlsbWriter
+import datetime
+from decimal import Decimal
+
+data = [
+    ["Name", "Age", "City", "info"],
+    [-123, 2147483647, 2147483648, 2147483999],
+    ["x", "y", "z", datetime.datetime.today()],
+    ["Alice", 25, "New York", datetime.date.today()],
+    ["Bob", 30, "London", Decimal(3.14)],
+    ["Charlie", 35, "Paris", datetime.datetime.now()],
+    [True, False, None, datetime.datetime.utcnow()]
+]
+
+writer = XlsbWriter("test.xlsb")
+writer.add_sheet("Sheet1")
+writer.write_sheet(data)
+writer.save()
+```

pyxlsbwriter-0.0.1/pyproject.toml

@@ -0,0 +1,31 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "pyxlsbwriter"
+version = "0.0.1"
+authors = [
+  { name="Krzysztof Duśko"},
+]
+description = "A Python library to write XLSB files."
+readme = "README.md"
+requires-python = ">=3.8"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "xlsxwriter"
+]
+
+[project.optional-dependencies]
+test = [
+    "pyodbc"
+]
+examples = [
+    "memory-profiler"
+]
+
+

pyxlsbwriter-0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

pyxlsbwriter-0.0.1/src/pyxlsbwriter/__init__.py

@@ -0,0 +1,3 @@
+from .writer import XlsbWriter
+
+__all__ = ['XlsbWriter']

pyxlsbwriter-0.0.1/src/pyxlsbwriter/writer.py

@@ -0,0 +1,618 @@
+from dataclasses import dataclass
+import datetime
+from decimal import Decimal
+import zipfile
+import struct
+from typing import  Tuple, Iterable
+import io
+import itertools
+
+@dataclass
+class FilterData:
+    sheet_index: int = 0
+    start_column: int = 0
+    end_column: int = 0  
+    start_row: int = 0
+    end_row: int = 0
+
+
+class XlsbWriter:
+    def __init__(self, filename: str):
+        self.filename = filename
+        self._worksheet_data: list[Tuple[str, Iterable[list[any]],bool]] = []
+        self._shared_strings: list[str] = []
+        self._shared_strings_dict: dict[str, int] = {}
+        self._sheet_count = 0
+        self._sst_unique_count = 0
+        self._sst_all_count = 0
+        self._filtered_data_list: list[FilterData] = []
+
+    def add_sheet(self, sheet_name: str):
+        self._sheet_count += 1
+        # Add a placeholder for the data iterable
+        self._worksheet_data.append((sheet_name, iter([])))
+
+    def write_sheet(self, data: Iterable[list[any]], hidden = False, compressionLevel:int = 4):
+        if not self._worksheet_data:
+            self.add_sheet("Sheet1")
+        
+        # Store the iterable without consuming it. Processing is deferred to save().
+        sheet_name, _ = self._worksheet_data[self._sheet_count - 1]
+        self._worksheet_data[self._sheet_count - 1] = (sheet_name, data,hidden)
+
+        if self._zf is None:
+            self._zf =  zipfile.ZipFile(self.filename, 'w', zipfile.ZIP_DEFLATED, compresslevel=compressionLevel)
+
+        for i, (sheet_name, sheet_data_iterable, _) in enumerate([self._worksheet_data[self._sheet_count - 1]]):
+            i = self._sheet_count - 1 
+            sheet_id = i + 1
+            with self._zf.open(f"xl/worksheets/sheet{sheet_id}.bin", 'w') as sheet_file:
+                self._write_worksheet_bin(sheet_file, sheet_data_iterable, i)
+            
+            self._zf.writestr(f"xl/worksheets/_rels/sheet{sheet_id}.bin.rels", self._create_worksheet_rels(sheet_id))
+            self._zf.writestr(f"xl/worksheets/binaryIndex{sheet_id}.bin", self._binaryIndexBin)
+
+    _zf: zipfile.ZipFile|None = None
+
+    def save(self):
+        self._zf.writestr("[Content_Types].xml", self._create_content_types())
+        self._zf.writestr("_rels/.rels", self._create_root_rels())
+        self._zf.writestr("xl/workbook.bin", self._create_workbook_bin())
+        self._zf.writestr("xl/styles.bin", self._stylesBin)
+        self._zf.writestr("xl/_rels/workbook.bin.rels", self._create_workbook_rels())
+
+        # After all worksheets are processed, the shared strings table is complete.
+        # Now, write it to the zip file in a streaming fashion.
+        with self._zf.open("xl/sharedStrings.bin", 'w') as sst_file:
+            self._write_shared_strings_bin(sst_file)
+        
+        self._zf.close()
+
+
+    def _create_content_types(self) -> str:
+        parts = "".join(
+            f'<Override PartName="/xl/worksheets/sheet{i + 1}.bin" ContentType="application/vnd.ms-excel.worksheet"/>'
+            f'<Override PartName="/xl/worksheets/binaryIndex{i + 1}.bin" ContentType="application/vnd.ms-excel.binIndexWs"/>'
+            for i in range(self._sheet_count)
+        )
+
+        return f'''<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">
+<Default Extension="bin" ContentType="application/vnd.ms-excel.sheet.binary.macroEnabled.main"/>
+<Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>
+<Default Extension="xml" ContentType="application/xml"/>
+<Override PartName="/xl/workbook.bin" ContentType="application/vnd.ms-excel.sheet.binary.macroEnabled.main"/>
+{parts}
+<Override PartName="/xl/styles.bin" ContentType="application/vnd.ms-excel.styles"/>
+<Override PartName="/xl/sharedStrings.bin" ContentType="application/vnd.ms-excel.sharedStrings"/>
+</Types>'''
+
+    def _create_root_rels(self) -> str:
+        return '''<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
+<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="xl/workbook.bin"/>
+</Relationships>'''
+
+    def _create_workbook_rels(self) -> str:
+        relationships = [
+            f'<Relationship Id="rId{i + 1}" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/worksheet" Target="worksheets/sheet{i + 1}.bin"/>'
+            for i in range(self._sheet_count)
+        ]
+        
+        style_rid = self._sheet_count + 1
+        shared_strings_rid = self._sheet_count + 2
+        relationships.append(f'<Relationship Id="rId{style_rid}" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles" Target="styles.bin"/>')
+        relationships.append(f'<Relationship Id="rId{shared_strings_rid}" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/sharedStrings" Target="sharedStrings.bin"/>')
+
+        return f'''<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
+{"".join(relationships)}
+</Relationships>'''
+
+    def _create_worksheet_rels(self, sheet_id) -> str:
+        return f'''<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
+<Relationship Id="rId1" Type="http://schemas.microsoft.com/office/2006/relationships/xlBinaryIndex" Target="binaryIndex{sheet_id}.bin"/>
+</Relationships>'''
+
+    def _create_workbook_bin(self) -> bytes:
+        data = bytearray(self._workbookBinStart)
+        for i, (sheet_name, _, hidden) in enumerate(self._worksheet_data):
+            sheet_id = i + 1
+            r_id = f"rId{sheet_id}"
+            
+            record_length = 4 + 3 * 4 + len(sheet_name) * 2 + len(r_id) * 2
+            
+            data.extend(b'\x9C\x01')
+            data.extend(self._write_custom_variable_int(record_length))
+            
+            if hidden:
+                data.extend(struct.pack('<I', 1))
+            else:
+                data.extend(struct.pack('<I', 0)) 
+
+            data.extend(struct.pack('<I', sheet_id))
+            data.extend(struct.pack('<I', len(r_id)))
+            data.extend(r_id.encode('utf-16-le'))
+            data.extend(struct.pack('<I', len(sheet_name)))
+            data.extend(sheet_name.encode('utf-16-le'))
+
+        data.extend(self._workbookBinMiddle)
+        self._write_filter_defined_names(data);
+        data.extend(self._workbookBinEnd)
+        return bytes(data)
+
+    def _write_custom_variable_int(self, value: int) -> bytes:
+        if value < 0:
+            raise ValueError("Value must be non-negative")
+        
+        buffer = bytearray()
+        temp_val = value
+        while True:
+            byte = temp_val & 0x7F
+            temp_val >>= 7
+            if temp_val > 0:
+                byte |= 0x80
+                buffer.append(byte)
+            else:
+                buffer.append(byte)
+                break
+        return bytes(buffer)
+
+    def _write_shared_strings_bin(self, sst_file: io.BufferedWriter):
+        buffer = io.BytesIO()
+        BUFFER_SIZE = 65536
+
+        buffer.write(b'\x9F\x01\x08')
+        buffer.write(struct.pack('<II', self._sst_all_count, self._sst_unique_count))
+        
+        for s in self._shared_strings:
+            str_len = len(s)
+            if str_len > 32767: 
+                str_len = 32767
+                s = s[:str_len]
+            
+            record_length = 1 + 4 + 2 * str_len
+            
+            buffer.write(b'\x13')
+            buffer.write(self._write_custom_variable_int(record_length))
+            buffer.write(b'\x00')
+            buffer.write(struct.pack('<I', str_len))
+            buffer.write(s.encode('utf-16-le'))
+
+            if buffer.tell() > BUFFER_SIZE:
+                sst_file.write(buffer.getvalue())
+                buffer.seek(0)
+                buffer.truncate()
+            
+        buffer.write(b'\xA0\x01\x00')
+        
+        if buffer.tell() > 0:
+            sst_file.write(buffer.getvalue())
+
+    def _write_cols_width(self, buffer: io.BytesIO, start_col: int, end_col: int, col_widths_array: list[float]):
+        """
+        Write column width information to the buffer.
+        Based on the C# WriteColsWidth method from XlsbWriter.cs
+        """
+        # widths !!!
+        buffer.write(b'\x86\x03')  # 134, 3
+        
+        l = 0
+        for i in range(start_col, end_col):
+            # start of column definition   
+            buffer.write(b'\x00\x3C\x12')  # 0, 60, 18
+            
+            # column min
+            buffer.write(struct.pack('<I', i))
+            # column max  
+            buffer.write(struct.pack('<I', i))
+            
+            # width
+            buffer.write(b'\x00')
+            buffer.write(struct.pack('<B', int(col_widths_array[l])))  # .. x 7 = pixels
+            buffer.write(b'\x00\x00')
+            
+            buffer.write(b'\x00\x00\x00\x00')
+            buffer.write(b'\x02')  # column properties /hidden etc, 2 = normal
+            # end of column definition   
+            l += 1
+            
+        buffer.write(b'\x00\x87\x03\x00')  # 0, 135, 3, 0
+
+    _sheetCnt = 1
+    def _write_worksheet_bin(self, sheet_file: io.BufferedWriter, worksheet_data: Iterable[list[any]], worksheet_index:int):
+        buffer = io.BytesIO()
+        BUFFER_SIZE = 65536
+
+        buffer.write(self._sheet1Bytes[:54])
+        if self._sheetCnt != 1:
+            buffer.write(b'\x9C')
+        else:
+            buffer.write(b'\xDC')
+        self._sheetCnt +=1
+
+        buffer.write(self._sheet1Bytes[55:84])
+
+        buffer.write(self._stickHeaderA1bytes)
+
+        # Calculate column information by reading first 100 rows for better width estimation
+        data_iterator = iter(worksheet_data)
+        rows_to_analyze = []
+        max_cols = 1
+        
+        # Read up to 100 rows for analysis
+        for _ in range(100):
+            try:
+                row = next(data_iterator)
+                rows_to_analyze.append(row)
+                max_cols = max(max_cols, len(row) if row else 0)
+            except StopIteration:
+                break  # No more rows available
+            
+        if max_cols == 0:
+            max_cols = 1
+            
+        start_col = 0
+        end_col = max_cols
+        
+        # Create column widths based on analyzed rows content
+        col_widths_array = []
+        for i in range(max_cols):
+            max_width = 0
+            for row in rows_to_analyze:
+                cell = row[i]
+                if i < len(row) and cell is not None:
+                    if cell is Decimal:
+                        cell = float(cell)
+                    lenn = len(str(cell))
+                    temp_width = 1.25 * lenn + 4
+                    max_width = max(max_width, temp_width)
+            
+            if max_width == 0:
+                max_width = 1.25 * 0 + 4  # Empty column
+            col_widths_array.append(max_width)
+        
+        # Create iterator that starts with analyzed rows, then continues with the rest
+        if rows_to_analyze:
+            data_iterator = itertools.chain(rows_to_analyze, data_iterator)
+        else:
+            data_iterator = iter([])
+
+        buffer.write(self._sheet1Bytes[84:159])
+        
+        # Write column widths
+        self._write_cols_width(buffer, start_col, end_col, col_widths_array)
+        
+        buffer.write(self._sheet1Bytes[159:175])
+        buffer.write(b'\x26\x00')
+        buffer.write(b'\x91\x01\x00')
+
+        shared_strings_dict = self._shared_strings_dict
+        shared_strings_append = self._shared_strings.append
+
+        for row_idx, row in enumerate(data_iterator):
+            last_col = len(row) - 1 if row else 0
+            
+            buffer.write(b'\x00\x19')
+            buffer.write(struct.pack('<I', row_idx))
+            buffer.write(b'\x00\x00\x00\x00')
+            buffer.write(struct.pack('<I', 0x12c))
+            buffer.write(b'\x00\x01\x00\x00\x00')
+            buffer.write(struct.pack('<II', 0, last_col))
+
+            for col_idx, cell in enumerate(row):
+                if cell is None:
+                    continue
+                if isinstance(cell, str):       
+                    self._sst_all_count += 1
+                    if cell not in shared_strings_dict:
+                        string_index = self._sst_unique_count
+                        shared_strings_dict[cell] = string_index
+                        shared_strings_append(cell)
+                        self._sst_unique_count += 1
+                    else:
+                        string_index = shared_strings_dict[cell]
+                    
+                    style_ref = 3 if row_idx == 0 else 0
+                    buffer.write(b'\x07\x0C')
+                    buffer.write(struct.pack('<III', col_idx, style_ref, string_index))
+                elif isinstance(cell, bool):
+                    buffer.write(b'\x04\x09')
+                    buffer.write(struct.pack('<IIB', col_idx, 0, 1 if cell else 0))
+                elif isinstance(cell, int):
+                    if -536870912 <= cell <= 536870911:
+                        rk_val = (cell << 2) | 0b10
+                        buffer.write(b'\x02\x0C')
+                        buffer.write(struct.pack('<IIi', col_idx, 0, rk_val))
+                    else:
+                        buffer.write(b'\x05\x10')
+                        buffer.write(struct.pack('<IId', col_idx, 0, float(cell)))
+                elif isinstance(cell, float):
+                    buffer.write(b'\x05\x10')
+                    buffer.write(struct.pack('<IId', col_idx, 0, cell))
+                elif isinstance(cell, Decimal):
+                    buffer.write(b'\x05\x10')
+                    buffer.write(struct.pack('<IId', col_idx, 0, float(cell)))
+                elif isinstance(cell, datetime.datetime):
+                    excel_date = (cell - datetime.datetime(1899, 12, 30)).total_seconds() / 86400.0
+                    buffer.write(b'\x05\x10')
+                    buffer.write(struct.pack('<IId', col_idx, 1, excel_date))
+                elif isinstance(cell, datetime.date):
+                    excel_date = (datetime.datetime.combine(cell, datetime.time()) - datetime.datetime(1899, 12, 30)).total_seconds() / 86400.0
+                    buffer.write(b'\x05\x10')
+                    buffer.write(struct.pack('<IId', col_idx, 2, excel_date))
+                else:
+                    cell_str = str(cell)
+                    self._sst_all_count += 1
+                    if cell_str not in shared_strings_dict:
+                        string_index = self._sst_unique_count
+                        shared_strings_dict[cell_str] = string_index
+                        shared_strings_append(cell_str)
+                        self._sst_unique_count += 1
+                    else:
+                        string_index = shared_strings_dict[cell_str]
+                    buffer.write(b'\x07\x0C')
+                    buffer.write(struct.pack('<III', col_idx, 0, string_index))
+            
+            if buffer.tell() > BUFFER_SIZE:
+                sheet_file.write(buffer.getvalue())
+                buffer.seek(0)
+                buffer.truncate()
+        
+        buffer.write(self._sheet1Bytes[218:290])
+
+        
+        # doAutofilter
+        buffer.write(self._autoFilterStartBytes)
+        buffer.write(struct.pack('<I', 0))
+        buffer.write(struct.pack('<I', row_idx))
+        buffer.write(struct.pack('<I', 0))
+        buffer.write(struct.pack('<I', 0 + end_col - 1))
+        buffer.write(self._autoFilterEndBytes)
+        self._filtered_data_list.append(
+            FilterData(
+            sheet_index=worksheet_index,
+            start_column=0,
+            end_column=end_col - 1,
+            start_row=0,
+            end_row=row_idx
+        ))
+
+        buffer.write(self._sheet1Bytes[290:])
+        if buffer.tell() > 0:
+            sheet_file.write(buffer.getvalue())
+
+    def _write_filter_defined_names(self, sw: bytearray) -> None:
+        filtered_dict_items_cnt = len(self._filtered_data_list) if self._filtered_data_list else 0
+        
+        # Temporary fix for https://github.com/KrzysztofDusko/SpreadSheetTasks/issues/2
+        if (filtered_dict_items_cnt >= 0 and 
+            (0x80 + (filtered_dict_items_cnt - 21) * 0x0c) <= 255):
+            
+            sw.extend(self._magicFilterExcel2016Fix0)
+            
+            if filtered_dict_items_cnt <= 10:
+                # !!! ? for cnt <=10
+                sw.extend(bytes([0x10 + (filtered_dict_items_cnt - 1) * 0x0c, 
+                               filtered_dict_items_cnt]))
+                sw.extend(bytes([0x00, 0x00, 0x00]))
+                
+            elif filtered_dict_items_cnt <= 20:
+                sw.extend(bytes([0x10 + (filtered_dict_items_cnt - 1) * 0x0c,
+                               (filtered_dict_items_cnt - 1) // 10,
+                               filtered_dict_items_cnt]))
+                sw.extend(bytes([0x00, 0x00, 0x00]))
+                
+            else:  # ???
+                sw.extend(bytes([0x80 + (filtered_dict_items_cnt - 21) * 0x0c,
+                               (filtered_dict_items_cnt - 1) // 10,
+                               filtered_dict_items_cnt]))
+                sw.extend(bytes([0x00, 0x00, 0x00]))
+            
+            # Write filter items
+            for nm in range(filtered_dict_items_cnt):
+                sw.extend(bytes([0x00, 0x00, 0x00, 0x00]))
+                sw.extend(bytes([self._filtered_data_list[nm].sheet_index, 0x00, 0x00, 0x00]))
+                sw.extend(bytes([self._filtered_data_list[nm].sheet_index, 0x00, 0x00, 0x00]))
+            
+            sw.extend(bytes([0xE2, 0x02, 0x00]))
+            
+            # Write sheet data
+            for sheet_num in range(len(self._filtered_data_list)):
+                start_column = self._filtered_data_list[sheet_num].start_column
+                end_column = self._filtered_data_list[sheet_num].end_column
+                start_row = self._filtered_data_list[sheet_num].start_row
+                end_row = self._filtered_data_list[sheet_num].end_row
+                sheet_index = self._filtered_data_list[sheet_num].sheet_index
+                
+                # Modify magic bytes
+                self._magicFilterExcel2016Fix1[7] = sheet_index
+                self._magicFilterExcel2016Fix1[-2] = sheet_num
+                sw.extend(self._magicFilterExcel2016Fix1)
+
+
+                # Write binary data using struct.pack for proper byte conversion
+                sw.extend(struct.pack('<I', start_row))  # Int32 little-endian
+                sw.extend(struct.pack('<I', end_row))    # Int32 little-endian
+                sw.extend(struct.pack('<H', start_column))  # Int16 little-endian
+                sw.extend(struct.pack('<H', end_column))    # Int16 little-endian
+                
+                sw.extend(self._magicFilterExcel2016Fix2)
+
+
+    _autoFilterStartBytes = bytes([0xA1, 0x01, 0x10])
+    _sheet1Bytes = bytes([
+        0x81,0x01,0x00,0x93,0x01,0x17,0xCB,0x04,0x02,0x00,0x40,0x00,0x00,0x00,0x00,0x00,0x00,0xFF,0xFF,0xFF,
+        0xFF,0xFF,0xFF,0xFF,0xFF,0x00,0x00,0x00,0x00,0x94,0x01,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x85,0x01,0x00,0x89,0x01,0x1E,0xDC,0x03,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x40,0x00,0x00,0x00,0x64,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x00,0x98,0x01,0x24,0x03,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x8A,0x01,0x00,0x86,0x01,0x00,0x25,0x06,0x01,0x00,0x02,0x0E,0x00,0x80,0x95,0x08,0x02,
+        0x05,0x00,0x26,0x00,0xE5,0x03,0x0C,0xFF,0xFF,0xFF,0xFF,0x08,0x00,0x2C,0x01,0x00,0x00,0x00,0x00,0x91,
+        0x01,0x00,0x25,0x06,0x01,0x00,0x02,0x0E,0x00,0x80,0x80,0x08,0x02,0x05,0x00,0x26,0x00,0x00,0x19,0x00,
+        0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x2C,0x01,0x00,0x00,0x00,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x00,0x07,0x0C,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x92,0x01,
+        0x00,0x97,0x04,0x42,0x00,0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00,0x00,0x01,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00,0x00,0xDD,0x03,0x02,0x10,0x00,0xDC,0x03,0x30,0x66,0x66,
+        0x66,0x66,0x66,0x66,0xE6,0x3F,0x66,0x66,0x66,0x66,0x66,0x66,0xE6,0x3F,0x00,0x00,0x00,0x00,0x00,0x00,
+        0xE8,0x3F,0x00,0x00,0x00,0x00,0x00,0x00,0xE8,0x3F,0x33,0x33,0x33,0x33,0x33,0x33,0xD3,0x3F,0x33,0x33,
+        0x33,0x33,0x33,0x33,0xD3,0x3F,0x25,0x06,0x01,0x00,0x00,0x10,0x00,0x80,0x80,0x18,0x10,0x00,0x00,0x00,
+        0x00,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x26,0x00,0x82,0x01,0x00
+    ])
+    _stylesBin = bytes([
+        0x96,0x02,0x00,0xE7,0x04,0x04,0x02,
+        0x00,0x00,0x00,0x2C,0x2C,0xA4,0x00,0x13,
+        0x00,0x00,0x00,0x79,0x00,0x79,0x00,0x79,
+        0x00,0x79,0x00,0x5C,0x00,0x2D,0x00,0x6D,
+        0x00,0x6D,0x00,0x5C,0x00,0x2D,0x00,0x64,
+        0x00,0x64,0x00,0x5C,0x00,0x20,0x00,0x68,
+        0x00,0x68,0x00,0x3A,0x00,0x6D,0x00,0x6D,
+        0x00,0x2C,0x1E,0xA6,0x00,0x0C,0x00,0x00,
+        0x00,0x79,0x00,0x79,0x00,0x79,0x00,0x79,
+        0x00,0x5C,0x00,0x2D,0x00,0x6D,0x00,0x6D,
+        0x00,0x5C,0x00,0x2D,0x00,0x64,0x00,0x64,
+        0x00,0xE8,0x04,0x00,0xE3,0x04,0x04,0x01,
+        0x00,0x00,0x00,
+        0x2B,0x27,0xDC,0x00,0x00,0x00,0x90,0x01,
+        0x00,0x00,0x00,0x02,0x00,0x00,0x07,0x01,
+        0x00,0x00,0x00,0x00,0x00,0xFF,0x02,0x07,
+        0x00,0x00,0x00,0x43,0x00,0x61,0x00,0x6C,
+        0x00,0x69,0x00,0x62,0x00,0x72,0x00,0x69,
+        0x00,
+        0x2B,0x27,0xDC,0x00,0x01,0x00,0xBC,0x02,
+        0x00,0x00,0x00,0x02,0xEE,0x00,0x07,0x01,
+        0x00,0x00,0x00,0x00,0x00,0xFF,0x02,0x07,
+        0x00,0x00,0x00,0x43,0x00,0x61,0x00,0x6C,
+        0x00,0x69,0x00,0x62,0x00,0x72,0x00,0x69,
+        0x00,
+        0x25,0x06,0x01,0x00,0x02,0x0E,0x00,0x80,0x81,0x08,0x00,0x26,0x00,0xE4,0x04,0x00,0xDB,0x04,0x04,0x02,0x00,0x00,0x00,
+        0x2D,0x44,0x00,0x00,0x00,0x00,0x03,0x40,0x00,0x00,0x00,0x00,0x00,0xFF,0x03,0x41,0x00,0x00,0xFF,0xFF,0xFF,0xFF,0x00,
+        0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x2D,0x44,0x11,0x00,0x00,0x00,0x03,0x40,0x00,0x00,0x00,0x00,0x00,0xFF,0x03,0x41,0x00,0x00,0xFF,0xFF,0xFF,0xFF,
+        0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0xDC,0x04,0x00,0xE5,0x04,0x04,0x01,0x00,0x00,0x00,0x2E,0x33,0x00,0x00,0x00,0x01,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x00,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xE6,0x04,0x00,0xF2,
+        0x04,0x04,0x01,0x00,0x00,0x00,0x2F,0x10,0xFF,0xFF,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x10,0x10,0x00,
+        0x00,0xF3,0x04,0x00,0xE9,0x04,0x04,
+        0x04,
+        0x00,0x00,0x00,
+        0x2F,0x10,0x00,0x00,0x00,0x00,    0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x10,0x10,0x00,0x00,
+        0x2F,0x10,0x00,0x00,0xA4,0x00,    0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x10,0x10,0x01,0x00,
+        0x2F,0x10,0x00,0x00,0xA6,0x00,    0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x10,0x10,0x01,0x00,
+        0x2F,0x10,0x00,0x00,0x00,0x01,    0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x10,0x10,0x00,0x00,
+        0xEA,0x04,0x00,0xEB,0x04,0x04,0x01,0x00,
+        0x00,0x00,0x25,0x06,0x01,0x00,0x02,0x11,0x00,0x80,0x80,0x18,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x00,0x00,0x00,0x26,0x00,0x30,0x1C,0x00,0x00,0x00,0x00,0x01,0x00,0x00,0x00,0x08,0x00,0x00,0x00,0x4E,
+        0x00,0x6F,0x00,0x72,0x00,0x6D,0x00,0x61,0x00,0x6C,0x00,0x6E,0x00,0x79,0x00,0xEC,0x04,0x00,0xF9,0x03,0x04,0x00,0x00,
+        0x00,0x00,0xFA,0x03,0x00,0xFC,0x03,0x50,0x00,0x00,0x00,0x00,0x11,0x00,0x00,0x00,0x54,0x00,0x61,0x00,0x62,0x00,0x6C,
+        0x00,0x65,0x00,0x53,0x00,0x74,0x00,0x79,0x00,0x6C,0x00,0x65,0x00,0x4D,0x00,0x65,0x00,0x64,0x00,0x69,0x00,0x75,0x00,
+        0x6D,0x00,0x32,0x00,0x11,0x00,0x00,0x00,0x50,0x00,0x69,0x00,0x76,0x00,0x6F,0x00,0x74,0x00,0x53,0x00,0x74,0x00,0x79,
+        0x00,0x6C,0x00,0x65,0x00,0x4C,0x00,0x69,0x00,0x67,0x00,0x68,0x00,0x74,0x00,0x31,0x00,0x36,0x00,0xFD,0x03,0x00,0x23,
+        0x04,0x02,0x0E,0x00,0x00,0xEB,0x08,0x00,0xF6,0x08,0x2A,0x00,0x00,0x00,0x00,0x11,0x00,0x00,0x00,0x53,0x00,0x6C,0x00,
+        0x69,0x00,0x63,0x00,0x65,0x00,0x72,0x00,0x53,0x00,0x74,0x00,0x79,0x00,0x6C,0x00,0x65,0x00,0x4C,0x00,0x69,0x00,0x67,
+        0x00,0x68,0x00,0x74,0x00,0x31,0x00,0xF7,0x08,0x00,0xEC,0x08,0x00,0x24,0x00,0x23,0x04,0x03,0x0F,0x00,0x00,0xB0,0x10,
+        0x00,0xB2,0x10,0x32,0x00,0x00,0x00,0x00,0x15,0x00,0x00,0x00,0x54,0x00,0x69,0x00,0x6D,0x00,0x65,0x00,0x53,0x00,0x6C,
+        0x00,0x69,0x00,0x63,0x00,0x65,0x00,0x72,0x00,0x53,0x00,0x74,0x00,0x79,0x00,0x6C,0x00,0x65,0x00,0x4C,0x00,0x69,0x00,
+        0x67,0x00,0x68,0x00,0x74,0x00,0x31,0x00,0xB3,0x10,0x00,0xB1,0x10,0x00,0x24,0x00,0x97,0x02,0x00
+    ])
+    _workbookBinStart = bytes([
+        0x83,0x01,0x00,0x80,0x01,0x32,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x02,0x00,0x00,0x00,0x78,0x00,0x6C,0x00,0x01,0x00,0x00,0x00,0x37,0x00,0x01,0x00,0x00,0x00,
+        0x36,0x00,0x05,0x00,0x00,0x00,0x32,0x00,0x34,0x00,0x33,0x00,0x32,0x00,0x36,0x00,0x99,0x01,0x0C,0x20,
+        0x00,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x25,0x06,0x01,0x00,0x03,0x0F,0x00,0x80,0x97,
+        0x10,0x34,0x18,0x00,0x00,0x00,0x43,0x00,0x3A,0x00,0x5C,0x00,0x73,0x00,0x71,0x00,0x6C,0x00,0x73,0x00,
+        0x5C,0x00,0x54,0x00,0x65,0x00,0x73,0x00,0x74,0x00,0x79,0x00,0x5A,0x00,0x61,0x00,0x70,0x00,0x69,0x00,
+        0x73,0x00,0x75,0x00,0x58,0x00,0x6C,0x00,0x73,0x00,0x62,0x00,0x5C,0x00,0x26,0x00,0x25,0x06,0x01,0x00,
+        0x00,0x10,0x00,0x80,0x81,0x18,0x82,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x2F,0x00,0x00,0x00,
+        0x31,0x00,0x33,0x00,0x5F,0x00,0x6E,0x00,0x63,0x00,0x72,0x00,0x3A,0x00,0x31,0x00,0x5F,0x00,0x7B,0x00,
+        0x31,0x00,0x36,0x00,0x35,0x00,0x30,0x00,0x38,0x00,0x44,0x00,0x36,0x00,0x39,0x00,0x2D,0x00,0x43,0x00,
+        0x46,0x00,0x38,0x00,0x37,0x00,0x2D,0x00,0x34,0x00,0x37,0x00,0x36,0x00,0x39,0x00,0x2D,0x00,0x38,0x00,
+        0x34,0x00,0x35,0x00,0x36,0x00,0x2D,0x00,0x44,0x00,0x34,0x00,0x41,0x00,0x34,0x00,0x30,0x00,0x31,0x00,
+        0x31,0x00,0x33,0x00,0x31,0x00,0x35,0x00,0x36,0x00,0x37,0x00,0x7D,0x00,0x2F,0x00,0x00,0x00,0x2F,0x00,
+        0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x26,0x00,
+        0x87,0x01,0x00,0x25,0x06,0x01,0x00,0x02,0x10,0x00,0x80,0x80,0x18,0x10,0x00,0x00,0x00,0x00,0x0D,0x00,
+        0x00,0x00,0xFF,0xFF,0xFF,0xFF,0x00,0x00,0x00,0x00,0x26,0x00,0x9E,0x01,0x1D,0x00,0x00,0x00,0x00,0x9E,
+        0x16,0x00,0x00,0xB4,0x69,0x00,0x00,0xE8,0x26,0x00,0x00,0x58,0x02,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x78,0x88,0x01,0x00,0x8F,0x01,0x00
+    ])
+    _workbookBinMiddle = bytes([0x90,0x01,0x00])
+    _workbookBinEnd = bytes([
+        0x9D,0x01,0x1A,0x35,0xEA,0x02,0x00,0x01,0x00,0x00,0x00,0x64,0x00,0x00,0x00,0xFC,0xA9,0xF1,0xD2,0x4D,
+        0x62,0x50,0x3F,0x01,0x00,0x00,0x00,0x6A,0x00,0x9B,0x01,0x01,0x00,0x23,0x04,0x03,0x0F,0x00,0x00,0xAB,
+        0x10,0x01,0x01,0x24,0x00,0x84,0x01,0x00
+    ])
+    _binaryIndexBin = bytes([
+        0x2A,0x18,0x00,0x00,0x00,0x00,0x20,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x00,0x00,0x00,0x95,0x02,0x00
+    ])
+    _stickHeaderA1bytes =bytes([
+        0x97,0x01,0x1D,0x00,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+        0x00,0xF0,0x3F,0x01,0x00,0x00,0x00,0x00,
+        0x00,0x00,0x00,0x02,0x00,0x00,0x00,0x03,
+    ])
+    _autoFilterEndBytes = bytes([0xA2, 0x01, 0x00])
+    _magicFilterExcel2016Fix0 = bytes([0xE1, 0x02, 0x00, 0xE5, 0x02, 0x00, 0xEA, 0x02])
+    _magicFilterExcel2016Fix1 = bytearray([
+            0x27,
+            0x46,
+            0x21,
+            0x00,
+            0x00,
+            0x00,
+            0x00,
+            255,# -> (byte)sheetIndex,
+            0x00,
+            0x00,
+            0x00,
+            0x0F,
+            0x00,
+            0x00,
+            0x00,
+            0x5F,
+            0x00,   # _0, // FilterDatabase (UTF16) - starts
+            0x46,
+            0x00,
+            0x69,
+            0x00,
+            0x6C,
+            0x00,
+            0x74,
+            0x00,
+            0x65,
+            0x00,
+            0x72,
+            0x00,
+            0x44,
+            0x00,
+            0x61,
+            0x00,
+            0x74,
+            0x00,
+            0x61,
+            0x00,
+            0x62,
+            0x00,
+            0x61,
+            0x00,
+            0x73,
+            0x00,
+            0x65,
+            0x00,# FilterDatabase (UTF16) - ends
+            0x0F,
+            0x00,
+            0x00,
+            0x00,
+            0x3B,
+            255,#->(byte)sheetNum,
+            0x00
+        ])
+    _magicFilterExcel2016Fix2 = bytes([0x00, 0x00, 0x00, 0x00, 0xFF, 0xFF, 0xFF, 0xFF])
+        

pyxlsbwriter-0.0.1/src/pyxlsbwriter.egg-info/PKG-INFO

@@ -0,0 +1,48 @@
+Metadata-Version: 2.4
+Name: pyxlsbwriter
+Version: 0.0.1
+Summary: A Python library to write XLSB files.
+Author: Krzysztof Duśko
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: xlsxwriter
+Provides-Extra: test
+Requires-Dist: pyodbc; extra == "test"
+Provides-Extra: examples
+Requires-Dist: memory-profiler; extra == "examples"
+
+# Python XLSB Writer
+
+A Python library for writing large data sets to XLSB files efficiently.
+
+## Installation
+
+```bash
+pip install pyxlsbwriter
+```
+
+## Usage
+
+```python
+from pyxlsbwriter import XlsbWriter
+import datetime
+from decimal import Decimal
+
+data = [
+    ["Name", "Age", "City", "info"],
+    [-123, 2147483647, 2147483648, 2147483999],
+    ["x", "y", "z", datetime.datetime.today()],
+    ["Alice", 25, "New York", datetime.date.today()],
+    ["Bob", 30, "London", Decimal(3.14)],
+    ["Charlie", 35, "Paris", datetime.datetime.now()],
+    [True, False, None, datetime.datetime.utcnow()]
+]
+
+writer = XlsbWriter("test.xlsb")
+writer.add_sheet("Sheet1")
+writer.write_sheet(data)
+writer.save()
+```

pyxlsbwriter-0.0.1/src/pyxlsbwriter.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+README.md
+pyproject.toml
+src/pyxlsbwriter/__init__.py
+src/pyxlsbwriter/writer.py
+src/pyxlsbwriter.egg-info/PKG-INFO
+src/pyxlsbwriter.egg-info/SOURCES.txt
+src/pyxlsbwriter.egg-info/dependency_links.txt
+src/pyxlsbwriter.egg-info/requires.txt
+src/pyxlsbwriter.egg-info/top_level.txt
+tests/test_real_data.py

pyxlsbwriter-0.0.1/src/pyxlsbwriter.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

pyxlsbwriter-0.0.1/src/pyxlsbwriter.egg-info/requires.txt

@@ -0,0 +1,7 @@
+xlsxwriter
+
+[examples]
+memory-profiler
+
+[test]
+pyodbc

pyxlsbwriter-0.0.1/src/pyxlsbwriter.egg-info/top_level.txt

@@ -0,0 +1 @@
+pyxlsbwriter

pyxlsbwriter-0.0.1/tests/test_real_data.py

@@ -0,0 +1,102 @@
+import os
+from typing import Generator
+import pyodbc
+from pyxlsbwriter import XlsbWriter
+
+# --- CONFIGURATION ---
+# CHANGE THE VALUES BELOW TO MATCH YOUR NETEZZA DATABASE
+# Make sure you have an ODBC data source (DSN) configured for Netezza on your system.
+password = os.environ.get("NZ_DEV_PASSWORD", "password")
+DSN = f"DRIVER={{NetezzaSQL}};SERVER=linux.local;PORT=5480;DATABASE=JUST_DATA;UID=admin;PWD={password};"
+# Sample query. Change it to one that works on your database.
+QUERY1 = "SELECT * FROM JUST_DATA..DIMACCOUNT"
+QUERY2 = "SELECT * FROM JUST_DATA..DIMCURRENCY"
+OUTPUT_FILENAME = "real_netezza_output.xlsb"
+
+
+def row_generator(cursor: pyodbc.Cursor) -> Generator[list[any], None, None]:
+    """
+    Generates rows from a pyodbc cursor, yielding headers first, followed by data rows.
+
+    Args:
+        cursor: A pyodbc cursor object containing query results.
+
+    Yields:
+        List[Any]: First yields the list of column headers, then each row as a list.
+
+    Raises:
+        pyodbc.Error: If there's an error accessing the cursor's data.
+    """
+    try:
+        # Extract column headers from cursor description
+        headers = [column[0] for column in cursor.description]
+        yield headers
+
+        # Yield each row until the cursor is exhausted
+        while row := cursor.fetchone():
+            yield list(row)
+    except pyodbc.Error as e:
+        raise pyodbc.Error(f"Error processing cursor data: {e}")
+
+def main():
+    """
+    Tests fetching data from a real Netezza database and writing to an XLSB file.
+    """
+    if os.path.exists(OUTPUT_FILENAME):
+        os.remove(OUTPUT_FILENAME)
+
+    try:
+        print(f"Connecting to the database using DSN: '{DSN.split(';')[0]}...'")
+        with pyodbc.connect(DSN) as conn:
+            cursor = conn.cursor()
+            print(f"Executing query: '{QUERY1}'")
+            cursor.execute(QUERY1)
+
+            # Use XlsbWriter to write the data
+            print(f"Writing data to file '{OUTPUT_FILENAME}'...")
+            writer = XlsbWriter(OUTPUT_FILENAME)
+            writer.add_sheet("Netezza Export")
+            writer.write_sheet(row_generator(cursor))
+
+            writer.add_sheet("query 2")
+            print(f"Executing query: '{QUERY2}'")
+            cursor.execute(QUERY2)
+            writer.write_sheet(row_generator(cursor))
+            writer.add_sheet("SQL1")
+            writer.write_sheet([["code"],[QUERY1]] ,hidden=True)
+            writer.add_sheet("SQL2")
+            writer.write_sheet([["code"],[QUERY2]] ,hidden=True)
+            writer.save()
+
+    except pyodbc.Error as ex:
+        sqlstate = ex.args[0]
+        print(f"Database connection or query execution error: {sqlstate}\n{ex}")
+    except Exception as e:
+        print(f"An unexpected error occurred: {e}")
+
+    # Check if the XLSB file was created and is not empty
+    if os.path.exists(OUTPUT_FILENAME) and os.path.getsize(OUTPUT_FILENAME) > 0:
+        print(f"\nTest completed successfully, file '{OUTPUT_FILENAME}' was created and contains data.")
+    else:
+        print(f"\nTest failed, file '{OUTPUT_FILENAME}' was not created or is empty.")
+
+    if os.path.exists(OUTPUT_FILENAME):
+        os.remove(OUTPUT_FILENAME)
+
+
+if __name__ == '__main__':
+    # Checking if pyodbc is installed
+    try:
+        import pyodbc
+        main()
+    except ImportError:
+        print("pyodbc library is not installed. Installing...")
+        import subprocess
+        import sys
+        try:
+            subprocess.check_call([sys.executable, "-m", "pip", "install", "pyodbc"])
+            main()
+        except subprocess.CalledProcessError as e:
+            print(f"Failed to install pyodbc. Please install it manually: pip install pyodbc")
+            sys.exit(1)
+