scribe/scraibe/email_sender.py

"""
Email sender module for ScrAIbe.

Sends transcription outputs (TXT, JSON, etc.) via SMTP.
All credentials are configured via environment variables.
Supports both plain text and HTML email bodies.
Template placeholders are primarily filled via environment variables.
"""

import base64
import json
import logging
import os
import re
import smtplib
from email import encoders
from email.mime.base import MIMEBase
from email.mime.multipart import MIMEMultipart
from email.mime.text import MIMEText
from typing import Any, Dict, List, Optional

from docx import Document
from docx.oxml import OxmlElement
from docx.oxml.ns import qn
from docx.shared import Inches, Pt
from docx.enum.text import WD_ALIGN_PARAGRAPH

logger = logging.getLogger("scraibe.email_sender")


class EmailError(Exception):
    pass


def get_email_config():
    """
    Read email configuration from environment variables.
    Raises EmailError if required fields are missing.
    """
    smtp_host = os.getenv("EMAIL_SMTP_HOST")
    smtp_port = os.getenv("EMAIL_SMTP_PORT")
    smtp_user = os.getenv("EMAIL_SMTP_USER")
    smtp_password = os.getenv("EMAIL_SMTP_PASSWORD")
    from_address = os.getenv("EMAIL_FROM_ADDRESS")
    use_tls_str = os.getenv("EMAIL_SMTP_USE_TLS", "true").strip().lower()
    use_tls = use_tls_str not in ("false", "0", "no")

    if not all([smtp_host, smtp_port, smtp_user, smtp_password, from_address]):
        raise EmailError(
            "Email configuration incomplete. "
            "Ensure EMAIL_SMTP_HOST, EMAIL_SMTP_PORT, EMAIL_SMTP_USER, "
            "EMAIL_SMTP_PASSWORD, and EMAIL_FROM_ADDRESS are set."
        )

    return {
        "smtp_host": smtp_host,
        "smtp_port": int(smtp_port),
        "smtp_user": smtp_user,
        "smtp_password": smtp_password,
        "from_address": from_address,
        "use_tls": use_tls,
    }


def _load_css(path: str) -> str:
    """
    Load CSS file content if it exists.
    """
    if not path or not os.path.exists(path):
        return ""
    with open(path, "r", encoding="utf-8") as f:
        return f.read()


def _email_logo_html() -> str:
    """
    Return a subtle watermark-style logo for emails.

    - Priority:
      1) EMAIL_LOGO_URL (direct URL)
      2) EMAIL_LOGO_PATH (local file as base64)
    - Style: small, faint, bottom-right, non-intrusive.
    """
    logo_url = os.getenv("EMAIL_LOGO_URL")
    src = logo_url

    if not logo_url:
        logo_path = os.getenv("EMAIL_LOGO_PATH", "/app/src/misc/logo1.png")
        if os.path.exists(logo_path):
            try:
                with open(logo_path, "rb") as f:
                    b64 = base64.b64encode(f.read()).decode("utf-8")
                src = f"data:image/png;base64,{b64}"
            except Exception:
                src = None

    if not src:
        return ""

    # Watermark: bottom-right, low opacity, compact
    return (
        f'<div style="text-align: right; margin-top: 24px; opacity: 0.15;">'
        f'<img src="{src}" alt="Logo" style="max-width: 90px; height: auto; display: inline-block;" />'
        f'</div>'
    )


def _accent_color() -> str:
    """
    Accent color for UI and emails.
    Default: #7C6DA0
    """
    return os.getenv("EMAIL_ACCENT_COLOR", "#7C6DA0")


def build_template_context(**runtime_kwargs: Any) -> Dict[str, Any]:
    """
    Build a context dict for templates from:
      - environment variables (base, customizable)
      - runtime-provided values (override env if present)

    Environment variables:
      - EMAIL_CONTACT_ADDRESS: value for {contact_email}
      - EMAIL_CSS_PATH: path to mail_style.css (optional; we inline it)
      - EMAIL_LOGO_URL: URL for email logo (preferred)
      - EMAIL_LOGO_PATH: fallback local path for email logo
      - EMAIL_ACCENT_COLOR: accent color (default #7C6DA0)
    """
    # Load and inline mail_style.css for consistent email styling
    css_path = os.getenv("EMAIL_CSS_PATH", "/app/src/misc/mail_style.css")
    css_text = _load_css(css_path)

    # Build logo HTML (URL or local fallback)
    logo_html = _email_logo_html()

    # Accent color
    accent = _accent_color()

    ctx: Dict[str, Any] = {
        "contact_email": os.getenv("EMAIL_CONTACT_ADDRESS", "support@example.com"),
        "email_css": css_text,
        "email_logo": logo_html,
        "accent_color": accent,
    }

    # Runtime values override env if provided
    if runtime_kwargs:
        ctx.update(runtime_kwargs)

    return ctx


def load_template(template_name: str, **runtime_kwargs: Any) -> str:
    """
    Load an HTML email template from misc/ and render placeholders.

    Expects files like:
        /app/src/misc/upload_notification_template.html
        /app/src/misc/success_template.html
        /app/src/misc/error_notification_template.html
    """
    base = os.getenv("SCRAIBE_TEMPLATES_DIR", "/app/src/misc")
    path = os.path.join(base, template_name)

    if not os.path.exists(path):
        raise EmailError(f"Email template not found: {path}")

    with open(path, "r", encoding="utf-8") as f:
        template = f.read()

    # Build context from env + runtime
    ctx = build_template_context(**runtime_kwargs)

    # Replace {placeholder} style variables safely
    try:
        return template.format(**ctx)
    except KeyError as e:
        raise EmailError(f"Missing template variable: {e}")


def send_email(
    to: str,
    subject: str,
    body: str,
    html: Optional[str],
    attachments: List[str],
    cc: Optional[str] = None,
) -> bool:
    """
    Send an email with optional HTML body and file attachments.

    Args:
        to: Comma-separated list of recipient email addresses.
        subject: Email subject.
        body: Email body (plain text).
        html: Email body (HTML), or None.
        attachments: List of file paths to attach.
        cc: Comma-separated list of CC email addresses (optional).

    Returns:
        True if sent successfully.

    Raises:
        EmailError if sending fails.
    """
    try:
        cfg = get_email_config()
    except EmailError as e:
        logger.error("Email configuration error: %s", e)
        raise

    # Parse recipients
    to_list = [addr.strip() for addr in to.split(",") if addr.strip()]
    cc_list = [addr.strip() for addr in cc.split(",") if addr.strip()] if cc else []

    if not to_list:
        raise EmailError("No valid 'To' email addresses provided.")

    # Ensure subject is never blank
    if not subject or not subject.strip():
        logger.warning("Subject was blank or missing; using default subject.")
        subject = "ScrAIbe: Your transcript is ready"

    subject = subject.strip()

    has_attachments = bool(attachments)

    # Build the text/HTML part (alternative)
    alt = MIMEMultipart("alternative")
    alt.attach(MIMEText(body, "plain"))
    if html:
        alt.attach(MIMEText(html, "html"))

    if has_attachments:
        # Outer message: multipart/mixed with headers
        msg = MIMEMultipart("mixed")
        msg["From"] = cfg["from_address"]
        msg["To"] = ", ".join(to_list)
        if cc_list:
            msg["Cc"] = ", ".join(cc_list)
        msg["Subject"] = subject

        # Attach the alternative (text/HTML) part
        msg.attach(alt)

        # Attach files
        for file_path in attachments:
            if not os.path.isfile(file_path):
                logger.warning("Attachment file not found, skipping: %s", file_path)
                continue

            try:
                with open(file_path, "rb") as f:
                    part = MIMEBase("application", "octet-stream")
                    part.set_payload(f.read())
                    encoders.encode_base64(part)
                    part.add_header(
                        "Content-Disposition",
                        "attachment",
                        filename=os.path.basename(file_path),
                    )
                    msg.attach(part)
            except Exception as e:
                logger.warning("Failed to attach file %s: %s", file_path, e)
    else:
        # No attachments: use the alternative part as the root message
        msg = alt
        msg["From"] = cfg["from_address"]
        msg["To"] = ", ".join(to_list)
        if cc_list:
            msg["Cc"] = ", ".join(cc_list)
        msg["Subject"] = subject

    # Connect and send
    try:
        if cfg["use_tls"]:
            server = smtplib.SMTP(cfg["smtp_host"], cfg["smtp_port"], timeout=30)
            server.ehlo()
            server.starttls()
            server.ehlo()
        else:
            server = smtplib.SMTP(cfg["smtp_host"], cfg["smtp_port"], timeout=30)
            server.ehlo()

        server.login(cfg["smtp_user"], cfg["smtp_password"])
        server.sendmail(
            cfg["from_address"],
            to_list + cc_list,
            msg.as_string(),
        )
        server.quit()
        logger.info(
            "Email sent to %s (CC: %s) with subject: %s",
            to_list,
            cc_list or "None",
            subject,
        )
        return True

    except Exception as e:
        logger.error("Failed to send email: %s", e)
        raise EmailError(f"Failed to send email: {e}")


# ------------ DOCX helpers ------------

def _configure_base_font(doc):
    """
    Set base document font to 12pt Courier.
    """
    style = doc.styles["Normal"]
    style.font.name = "Courier"
    style.font.size = Pt(12)


def _configure_section_margins(doc, margin=1.0):
    """
    Set uniform margins on all sides (default 1 inch).
    """
    for section in doc.sections:
        section.left_margin = Inches(margin)
        section.right_margin = Inches(margin)
        section.top_margin = Inches(margin)
        section.bottom_margin = Inches(margin)


def _enable_line_numbering(section, start_at=1, count_by=1, restart=True):
    """
    Enable line numbering for a specific section.
    """
    sectPr = section._sectPr

    # Create the line numbering element: <w:lnNumType>
    lnNumType = OxmlElement("w:lnNumType")
    lnNumType.set(qn("w:start"), str(start_at))
    lnNumType.set(qn("w:countBy"), str(count_by))

    # 'eachPage' restarts numbering on every page; 'continuous' keeps it going
    restart_mode = "eachPage" if restart else "continuous"
    lnNumType.set(qn("w:restart"), restart_mode)

    sectPr.append(lnNumType)


def _add_transcript_content(doc, text):
    """
    Add transcript lines to the document with formatting.
    """
    lines = text.strip().split("\n")
    for line in lines:
        line = line.strip()
        if not line:
            continue

        m = re.match(r"\[(\d+:\d+(?::\d+)?)\]\s*(.+?):\s*(.*)", line)
        if m:
            ts, speaker, content = m.groups()
            p = doc.add_paragraph()
            p.paragraph_format.left_indent = Inches(0.25)

            run_label = p.add_run(f"[{ts}] {speaker.upper()}:")
            run_label.bold = False
            run_label.underline = True
            run_label.font.name = "Courier"
            run_label.font.size = Pt(12)

            run_space = p.add_run(" ")
            run_space.bold = False
            run_space.underline = False
            run_space.font.name = "Courier"
            run_space.font.size = Pt(12)

            run_txt = p.add_run(content.strip())
            run_txt.bold = False
            run_txt.underline = False
            run_txt.font.name = "Courier"
            run_txt.font.size = Pt(12)
        else:
            p = doc.add_paragraph()
            run = p.add_run(line)
            run.font.name = "Courier"
            run.font.size = Pt(12)


def _add_summary_content(doc, text):
    """
    Add summary content with heading styles.
    """
    heading_count = 0
    for line in text.splitlines():
        stripped = line.strip()
        if not stripped:
            continue

        # Detect markdown-style headings: #, ##, ###, #### at start of line
        m = re.match(r"^(#{1,4})\s+(.*)", stripped)
        if m:
            heading_count += 1
            content = m.group(2).strip()

            p = doc.add_paragraph()
            p.paragraph_format.space_after = Pt(4)

            run = p.add_run(content)
            run.font.name = "Courier"
            run.font.size = Pt(12)

            # Apply formatting based on this heading's ordinal position
            if heading_count == 1:
                run.bold = True
            elif heading_count == 2:
                run.italic = True
            elif heading_count == 3:
                run.underline = True
            elif heading_count >= 4:
                run.italic = True
                run.underline = True
        else:
            # Normal text line
            p = doc.add_paragraph(stripped)
            p.paragraph_format.space_after = Pt(4)


# ------------ Public DOCX functions ------------

def create_transcript_docx(
    text: str,
    filename: str,
):
    """
    Create a .docx transcript with:
      - 1" margins on all sides
      - 12pt Courier
      - Continuous line numbering on the left
      - No cover page (standalone transcript only).
    """
    doc = Document()
    _configure_base_font(doc)
    _configure_section_margins(doc)

    # Fully clear default paragraphs so Word's line numbering starts at line 1
    body = doc.element.body
    for p in body.findall(qn('w:p')):
        body.remove(p)

    # Enable line numbering for transcript section
    _enable_line_numbering(doc.sections[0])

    # Transcript content (with line numbering)
    _add_transcript_content(doc, text)

    doc.save(filename)


def create_summary_docx(
    text: str,
    filename: str,
):
    """
    Create a .docx summary with consistent font and heading styles.
    No cover page, no line numbering.
    """
    doc = Document()
    _configure_base_font(doc)
    _configure_section_margins(doc)

    # Summary content (no line numbering)
    _add_summary_content(doc, text)

    doc.save(filename)