Fix/hash pattern scope

my_first_preswald_app/.gitignore

@@ -0,0 +1,3 @@
+secrets.toml
+.preswald_deploy
+.env.structured

my_first_preswald_app/data/sample.csv

@@ -0,0 +1,11 @@
+item,quantity,value
+Item A,10,100
+Item B,5,60
+Item C,8,80
+Item D,12,150
+Item E,7,90
+Item F,9,110
+Item G,4,50
+Item H,11,130
+Item I,6,70
+Item J,3,40

my_first_preswald_app/hello.py

@@ -0,0 +1,129 @@
+import pandas as pd
+import plotly.express as px
+from preswald import text, connect, slider, selectbox, plotly
+import logging
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+try:
+    # Initialize preswald
+    connect()
+
+    # Title
+    text("# 📈 Superstore Sales & Profit Dashboard")
+
+    # Load and preprocess
+    df = pd.read_csv("data/my_sample_superstore.csv")
+    print("Initial DataFrame shape:", df.shape)
+    print("Columns:", df.columns.tolist())
+
+    df["Order Date"]     = pd.to_datetime(df["Order Date"], format="%m/%d/%Y")
+    df["Profit Margin"]  = df["Profit"] / df["Sales"]
+
+    # State name to abbreviation mapping
+    state_abbrev = {
+        'Alabama': 'AL', 'Alaska': 'AK', 'Arizona': 'AZ', 'Arkansas': 'AR', 'California': 'CA',
+        'Colorado': 'CO', 'Connecticut': 'CT', 'Delaware': 'DE', 'Florida': 'FL', 'Georgia': 'GA',
+        'Hawaii': 'HI', 'Idaho': 'ID', 'Illinois': 'IL', 'Indiana': 'IN', 'Iowa': 'IA',
+        'Kansas': 'KS', 'Kentucky': 'KY', 'Louisiana': 'LA', 'Maine': 'ME', 'Maryland': 'MD',
+        'Massachusetts': 'MA', 'Michigan': 'MI', 'Minnesota': 'MN', 'Mississippi': 'MS', 'Missouri': 'MO',
+        'Montana': 'MT', 'Nebraska': 'NE', 'Nevada': 'NV', 'New Hampshire': 'NH', 'New Jersey': 'NJ',
+        'New Mexico': 'NM', 'New York': 'NY', 'North Carolina': 'NC', 'North Dakota': 'ND', 'Ohio': 'OH',
+        'Oklahoma': 'OK', 'Oregon': 'OR', 'Pennsylvania': 'PA', 'Rhode Island': 'RI', 'South Carolina': 'SC',
+        'South Dakota': 'SD', 'Tennessee': 'TN', 'Texas': 'TX', 'Utah': 'UT', 'Vermont': 'VT',
+        'Virginia': 'VA', 'Washington': 'WA', 'West Virginia': 'WV', 'Wisconsin': 'WI', 'Wyoming': 'WY'
+    }
+
+    # Convert state names to abbreviations
+    print("\nUnique states before mapping:", df['State'].unique())
+    df['State_Code'] = df['State'].map(state_abbrev)
+    print("Unique state codes after mapping:", df['State_Code'].unique())
+
+    # Sidebar widgets
+    min_sales   = slider(
+        "Minimum Sales Filter",
+        min_val=0,
+        max_val=int(df["Sales"].max()),
+        default=0
+    )
+    segment_sel = selectbox(
+        "Choose Segment",
+        options=sorted(df["Segment"].unique().tolist()),
+        default="Consumer"
+    )
+
+    # Apply filters
+    df = df[(df["Sales"] >= min_sales) & (df["Segment"] == segment_sel)]
+    print("\nDataFrame shape after filtering:", df.shape)
+
+    # 1. Sales vs. Profit by Category
+    text("## 1. Sales & Profit by Category")
+    cat_stats = df.groupby("Category", as_index=False).agg(
+        Total_Sales = ("Sales", "sum"),
+        Total_Profit = ("Profit", "sum")
+    )
+    fig1 = px.bar(
+        cat_stats,
+        x="Category",
+        y=["Total_Sales", "Total_Profit"],
+        barmode="group",
+        title="Sales and Profit by Category",
+        labels={"value": "USD", "variable": "Measure"},
+        color_discrete_sequence=px.colors.qualitative.Set2
+    )
+    fig1.update_layout(template="plotly_white")
+    plotly(fig1)
+
+    # 2. Average Profit Margin by Region
+    text("## 2. Average Profit Margin by Region")
+    region_stats = df.groupby("Region", as_index=False)["Profit Margin"]\
+                     .mean().rename(columns={"Profit Margin": "Avg_Profit_Margin"})
+    fig2 = px.bar(
+        region_stats,
+        x="Region",
+        y="Avg_Profit_Margin",
+        title="Average Profit Margin by Region",
+        labels={"Avg_Profit_Margin": "Profit Margin"},
+        color="Avg_Profit_Margin",
+        color_continuous_scale="Viridis"
+    )
+    fig2.update_layout(template="plotly_white")
+    plotly(fig2)
+
+    # 3. Segment-Specific Profit Margin by Category
+    text(f"## 3. Profit Margin by Category: {segment_sel}")
+    seg_cat = df.groupby("Category", as_index=False)["Profit Margin"]\
+                .mean().rename(columns={"Profit Margin": "Profit_Margin"})
+    fig3 = px.bar(
+        seg_cat,
+        x="Category",
+        y="Profit_Margin",
+        title=f"{segment_sel} Segment: Profit Margin by Category",
+        labels={"Profit_Margin": "Profit Margin"},
+        color_discrete_sequence=px.colors.sequential.Viridis
+    )
+    fig3.update_layout(template="plotly_white")
+    plotly(fig3)
+
+    # 4. Total Sales by State (USA Map)
+    text("## 4. Total Sales by State (USA)")
+    state_sales = df.groupby("State_Code", as_index=False)["Sales"].sum()
+    print("\nState sales data:")
+    print(state_sales)
+    fig4 = px.choropleth(
+        state_sales,
+        locations="State_Code",
+        locationmode="USA-states",
+        color="Sales",
+        scope="usa",
+        title="Total Sales by State",
+        labels={"Sales": "Total Sales"},
+        color_continuous_scale="Viridis"
+    )
+    fig4.update_layout(template="plotly_white")
+    plotly(fig4)
+
+except Exception as e:
+    logger.error(f"Error in main function: {e}")

my_first_preswald_app/preswald.toml

@@ -0,0 +1,20 @@
+[project]
+title = "Superstore Analysis Dashboard"
+version = "0.1.0"
+port = 8501
+slug = "my-first-preswald-app-540052"  
+entrypoint = "hello.py"    
+
+[branding]
+name = "Superstore Analysis Dashboard"
+logo = "images/logo.png"
+favicon = "images/favicon.ico"
+primaryColor = "#F89613"
+
+[data.my_sample_superstore]
+type = "csv"
+path = "data/my_sample_superstore.csv"
+
+[logging]
+level = "INFO"  
+format = "%(asctime)s - %(name)s - %(levelname)s - %(message)s"

my_first_preswald_app/pyproject.toml

@@ -0,0 +1,23 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "preswald-app"
+version = "0.1.0"
+description = "A Preswald application"
+requires-python = ">=3.8"
+dependencies = [
+    "preswald"
+]
+
+[tool.hatch.build.targets.wheel]
+packages = ["."]
+
+[tool.black]
+line-length = 88
+target-version = ['py38']
+
+[tool.isort]
+profile = "black"
+multi_line_output = 3

my_first_preswald_app/requirements.txt

@@ -0,0 +1,3 @@
+pandas>=2.0.0
+plotly>=5.0.0
+preswald 

preswald/engine/utils.py

@@ -4,14 +4,17 @@
 import re
 import zlib
 from datetime import date, datetime
-from typing import Any
+from typing import Any, Dict, List, Optional, Set, Tuple, Union
 
 import msgpack
 import numpy as np
 
 
 logger = logging.getLogger(__name__)
 
+# Compiled regex pattern for matching SHA-256 hashes
+HASH_PATTERN = re.compile(r"^[0-9a-f]{64}$")
+
 
 class PreswaldJSONEncoder(json.JSONEncoder):
     """Custom JSON encoder for Preswald data types."""
@@ -196,24 +199,23 @@ class RenderBuffer:
     Used by services to avoid redundant component reruns and frontend updates.
     """
 
-    HASH_PATTERN = re.compile(r"^[0-9a-f]{64}$")
-
     def __init__(self):
-        self._state_cache: dict[str, str] = {}
+        self._cache: Dict[str, str] = {}
+        self._dirty: Set[str] = set()
 
     def has_changed(self, component_id: str, new_value: Any) -> bool:
         """Check if the new hash differs from the cached one."""
         new_clean = clean_nan_values(new_value)
 
-        if component_id not in self._state_cache:
+        if component_id not in self._cache:
             return True  # always render the first time
 
-        old_clean = clean_nan_values(self._state_cache[component_id])
+        old_clean = clean_nan_values(self._cache[component_id])
         return new_clean != old_clean
 
     def update(self, component_id: str, new_value: Any):
         """Update the cached hash value."""
-        self._state_cache[component_id] = self._ensure_hash(new_value)
+        self._cache[component_id] = self._ensure_hash(new_value)
 
     def should_render(self, component_id: str, new_value: Any) -> bool:
         """
@@ -224,7 +226,7 @@ def should_render(self, component_id: str, new_value: Any) -> bool:
 
     def _ensure_hash(self, value: Any) -> str:
         """Convert value to SHA256 hash. Accepts either a hash string or a hashable object."""
-        if isinstance(value, str) and self.HASH_PATTERN.match(value):
+        if isinstance(value, str) and HASH_PATTERN.match(value):
             return value  # already a hash
         try:
             cleaned = clean_nan_values(value)