import pandas as pd
import plotly.express as px
import tempfile

def update_vh(vh_len):
    return vh_len
def update_vl(vl_len):
    return vl_len

#def make_fasta_file(df: pd.DataFrame):
#    if df.empty:
#        return None
#    lines = []
#    i = 1
#    for _, row in df.iterrows():
#        header = f">{i}_{row['vcall_VH']}|{row['Disease']}"
#        lines.append(header)
#        lines.append(row['VH'])
#        header = f">{i}_{row['vcall_VL']}|{row['Disease']}"
#        lines.append(header)
#        lines.append(row['VL'])
#    tmp = tempfile.NamedTemporaryFile(delete=False, suffix=".fasta")
#    tmp.write("\n".join(lines).encode())
#    tmp.close()
#    return tmp.name

def make_fasta_file(df: pd.DataFrame):
    """
    Vectorized FASTA file creation - ~100x faster than loop-based approach.
    Optimized for large datasets (1M+ sequences).
    """
    if df.empty:
        return None
    
    import numpy as np
    
    # Create sequence IDs as a vector
    n_seqs = len(df)
    seq_ids = np.arange(1, n_seqs + 1)
    
    # Vectorized header creation using string concatenation
    vh_headers = ">" + seq_ids.astype(str) + "_" + df['vcall_VH'].astype(str) + "|" + df['Disease'].astype(str) + "|VH"
    vl_headers = ">" + seq_ids.astype(str) + "_" + df['vcall_VL'].astype(str) + "|" + df['Disease'].astype(str) + "|VL"
    
    # Interleave headers and sequences using numpy array indexing
    fasta_content = np.empty((n_seqs * 4,), dtype=object)
    fasta_content[0::4] = vh_headers  # VH headers at positions 0, 4, 8, ...
    fasta_content[1::4] = df['VH'].astype(str)  # VH sequences at positions 1, 5, 9, ...
    fasta_content[2::4] = vl_headers  # VL headers at positions 2, 6, 10, ...
    fasta_content[3::4] = df['VL'].astype(str)  # VL sequences at positions 3, 7, 11, ...
    
    # Write to file in one operation (much faster than multiple writes)
    tmp = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix=".fasta", newline='')
    tmp.write('\n'.join(fasta_content))
    tmp.close()
    return tmp.name


def pie_vcall_vh(df: pd.DataFrame, total_raws: int, width: int = 500, height: int = 400) -> px.pie:

    current_count = len(df)
    remaining = total_raws - current_count
    values = [current_count, remaining]
    #labels = ['Selected', 'Remaining']
    fig = px.pie(values=values)
    fig.update_layout(width=width, height=height)
    return fig

def bar_vcall_vh(df: pd.DataFrame, total_rows: int, vh_germline: str,
                 width: int = 500, height: int = 250) -> px.bar:
    """
    Horizontal bar chart showing Selected vs Remaining counts.

    Parameters
    ----------
    df : pd.DataFrame
        Filtered dataframe from your query.
    total_rows : int
        Total number of rows in the full database.
    width, height : int
        Size of the resulting figure in pixels.
    """
    current_count = len(df)
    remaining = total_rows - current_count
    
    label_selected = vh_germline if vh_germline else "All Germlines"

    plot_df = pd.DataFrame({
        "Category": [label_selected, "Remaining"],
        "Count": [current_count, remaining]
    })

    fig = px.bar(
        plot_df,
        x="Count",
        y="Category",
        orientation="h",         # horizontal bars
        text="Count",            # show numbers on bars
        color="Category",
        color_discrete_map={
            "Selected Germline": "#3A7",  # greenish
            "Remaining": "#0000FF"           # gray #999
        }
    )

    fig.update_layout(
        width=width,
        height=height,
        showlegend=False,
        plot_bgcolor="white",
        xaxis_title="Number of Sequences",
    )

    return fig

def bar_vcall_vl(df: pd.DataFrame, total_rows: int, vl_germline: str,
                 width: int = 500, height: int = 250) -> px.bar:
    """
    Horizontal bar chart showing Selected vs Remaining counts.

    Parameters
    ----------
    df : pd.DataFrame
        Filtered dataframe from your query.
    total_rows : int
        Total number of rows in the full database.
    width, height : int
        Size of the resulting figure in pixels.
    """
    current_count = len(df)
    remaining = total_rows - current_count
    
    label_selected = vl_germline if vl_germline else "All Germlines"

    plot_df = pd.DataFrame({
        "Category": [label_selected, "Remaining"],
        "Count": [current_count, remaining]
    })

    fig = px.bar(
        plot_df,
        x="Count",
        y="Category",
        orientation="h",         # horizontal bars
        text="Count",            # show numbers on bars
        color="Category",
        color_discrete_map={
            "Selected Germline": "#3A7",  # greenish
            "Remaining": "#0000FF"           # gray #999
        }
    )


    fig.update_layout(
        width=width,
        height=height,
        showlegend=False,
        plot_bgcolor="white",
        xaxis_title="Number of Sequences",
    )

    return fig

def bar_disease_count(df: pd.DataFrame,
                      total_rows: int,
                      disease: str,
                      width: int = 500,
                      height: int = 250) -> px.bar:
    """
    Horizontal bar chart showing the count for the selected Disease
    versus all remaining rows in the database.

    Parameters
    ----------
    df : pd.DataFrame
        Filtered dataframe from your query (the rows matching filters).
    total_rows : int
        Total number of rows in the full database.
    disease : str
        Disease name chosen in the UI (e.g., "SARS-COV-2").
    width, height : int
        Size of the resulting figure.
    """
    current_count = len(df)
    remaining = total_rows - current_count

    label_selected = disease if disease else "All Diseases"

    plot_df = pd.DataFrame({
        "Category": [label_selected, "Remaining"],
        "Count": [current_count, remaining]
    })

    fig = px.bar(
        plot_df,
        x="Count",
        y="Category",
        orientation="h",
        color="Category",
        color_discrete_map={label_selected: "#d62728", "Remaining": "#999"}  # red & gray
    )

    # Remove all labels/legend for a clean look
    fig.update_layout(
        width=width,
        height=height,
        showlegend=False,
        plot_bgcolor="white",
    )

    return fig

def bar_btype_count(df: pd.DataFrame,
                    total_rows: int,
                    btype: str,
                    width: int = 500,
                    height: int = 250) -> px.bar:
    """
    Horizontal bar chart showing the count for the selected B-cell type
    versus the remaining rows in the database.

    Parameters
    ----------
    df : pd.DataFrame
        Filtered dataframe from your query (rows matching filters).
    total_rows : int
        Total number of rows in the full database.
    btype : str
        B-cell type selected in the UI (e.g., "Memory-B-Cells").
    width, height : int
        Size of the figure in pixels.
    """
    current_count = len(df)
    remaining = total_rows - current_count

    label_selected = btype if btype else "All B-Types"

    plot_df = pd.DataFrame({
        "Category": [label_selected, "Remaining"],
        "Count": [current_count, remaining]
    })

    fig = px.bar(
        plot_df,
        x="Count",
        y="Category",
        orientation="h",
        color="Category",
        color_discrete_map={label_selected: "#1f77b4",  # blue
                            "Remaining": "#999"}        # gray
    )

    fig.update_layout(
        width=width,
        height=height,
        showlegend=False,
        plot_bgcolor="white",
    )

    return fig

def hist_vh_vl_separate(df: pd.DataFrame,
                    width: int = 500,
                    height: int = 250) -> tuple[px.histogram, px.histogram]:
     """
     Returns two separate histograms: one for VH_length, one for VL_length.
     """

     vh_fig = px.histogram(
         df,
         x="VH_length",
         nbins=40,
         color_discrete_sequence=["#ff5c77"],  #blue
         labels={"count": "Count"}
     )
     vh_fig.update_layout(width=width, height=height,
                          plot_bgcolor="white",
                          yaxis_title="Count"
                          )
 
     vl_fig = px.histogram(
         df,
         x="VL_length",
         nbins=40,
         color_discrete_sequence=["#00ffff"],  # VL color (red)
         labels={"count": "Count"}
     )
     vl_fig.update_layout(width=width, height=height,
                          plot_bgcolor="white",
                          yaxis_title="Count"
                          )
 
     return vh_fig, vl_fig

def bar_vh_vl_combined(
    df: pd.DataFrame,
    total_rows: int,
    vh_germline: str | None,
    vl_germline: str | None,
    width: int = 500,
    height: int = 250
) -> px.bar:
    """
    Horizontal bar chart with three bars:
      1. Selected VH germline count
      2. Selected VL germline count
      3. Remaining = (2 * total_rows) - VH_count - VL_count
    """

    # Count VH matches
    if vh_germline:
        vh_count = (df["vcall_VH"] == vh_germline).sum()
    else:
        vh_count = len(df)

    # Count VL matches
    if vl_germline:
        vl_count = (df["vcall_VL"] == vl_germline).sum()
    else:
        vl_count = len(df)

    # Remaining sequences = 2 * total_rows - VH_count - VL_count
    remaining = (2 * total_rows) - (vh_count + vl_count)

    plot_df = pd.DataFrame({
        "Category": [
            vh_germline if vh_germline else "All Germlines",
            vl_germline if vl_germline else "All Germlines",
            "Remaining"
        ],
        "Count": [vh_count, vl_count, remaining]
    })

    fig = px.bar(
        plot_df,
        x="Count",
        y="Category",
        orientation="h",
        text="Count",
        color="Category",
        color_discrete_map={
            (vh_germline if vh_germline else "All Germlines"): "#3A7",
            (vl_germline if vl_germline else "All Germlines"): "#FF7F0E",
            "Remaining": "#0000FF"
        }
    )

    fig.update_layout(
        width=width,
        height=height,
        showlegend=False,
        plot_bgcolor="white",
        xaxis_title="Number of Sequences",
    )

    return fig

def bar_year_count(
    df: pd.DataFrame,
    width: int = 500,
    height: int = 250
) -> px.bar:
    """
    Horizontal bar chart of sequence counts per Year.

    Parameters
    ----------
    df : pd.DataFrame
        DataFrame that includes a 'Year' column.
    width, height : int
        Size of the figure.

    Returns
    -------
    plotly.graph_objects.Figure
    """
    if "Year" not in df.columns:
        raise ValueError("DataFrame must contain a 'Year' column.")

    # Count sequences per year and sort descending
    year_counts = 2 *df["Year"].value_counts().sort_index()

    # Create a DataFrame for plotting
    plot_df = pd.DataFrame({
        'Year': year_counts.index.astype(str),
        'Count': year_counts.values
    })
    
    fig = px.bar(
        plot_df,
        x='Count',
        y='Year',
        orientation="h",
        text='Count',
        color="Year",                 # <─ use Year as the color key
        color_discrete_sequence=px.colors.qualitative.Light24  # or any palette you like
    )

    fig.update_layout(
        width=width,
        height=height,
        plot_bgcolor="white",
        paper_bgcolor="white",
        xaxis_title="Number of Sequences",
        yaxis_title="Year",
        showlegend=False
    )
    # Remove grid lines for a cleaner look
    fig.update_xaxes(showgrid=False)
    fig.update_yaxes(showgrid=False)

    return fig