pediatric-ai-scribe-v3/scripts/render_pptx.py

#!/usr/bin/env python3
"""Render a slide deck from a JSON spec on stdin to a .pptx file.

Replaces pandoc's pptx writer, which could only map markdown onto a handful of
reference layouts. Everything that made those decks look generated is decided
here instead: which layout a slide gets, how large its text is, where an image
sits and at what aspect ratio, how a table is drawn.

Input (stdin, JSON):
  {"title": str, "subtitle": str, "date": str,
   "slides": [ {...} ],
   "images": [ "/abs/path.png", ... ] }

Each slide is one of:
  {"type": "title",   "heading": str, "subtitle": str}
  {"type": "section", "heading": str}
  {"type": "bullets", "heading": str, "bullets": [{"text":str,"level":int}], "notes": str}
  {"type": "two",     "heading": str, "left": [...], "right": [...]}
  {"type": "table",   "heading": str, "header": [str], "rows": [[str]]}
  {"type": "image",   "heading": str, "image": str, "caption": str}

Output: argv[1], a .pptx path. Errors go to stderr and exit non-zero, so the
caller can fall back rather than ship a broken file.
"""
import json
import sys
import os

from pptx import Presentation
from pptx.util import Emu, Pt
from pptx.dml.color import RGBColor
from pptx.enum.text import PP_ALIGN, MSO_ANCHOR

try:
    from PIL import Image
except Exception:  # pragma: no cover - Pillow is installed alongside
    Image = None

# 16:9. Pandoc's default reference doc is 4:3, which is why those decks looked
# dated before anything else about them did.
SLIDE_W = Emu(12192000)
SLIDE_H = Emu(6858000)

MARGIN = Emu(685800)          # 0.75"
HEADING_TOP = Emu(457200)     # 0.5"
HEADING_H = Emu(1005840)      # 1.1"
BODY_TOP = HEADING_TOP + HEADING_H + Emu(228600)   # clears the accent rule
BODY_H = SLIDE_H - BODY_TOP - MARGIN
BODY_W = SLIDE_W - MARGIN * 2

INK = RGBColor(0x1F, 0x29, 0x37)
MUTED = RGBColor(0x4B, 0x55, 0x63)
ACCENT = RGBColor(0x25, 0x63, 0xEB)
RULE = RGBColor(0xE5, 0xE7, 0xEB)
PAPER = RGBColor(0xFF, 0xFF, 0xFF)

FONT = "Calibri"

# Text is sized to fit rather than left to the renderer's autofit, which only
# some viewers honour and which LibreOffice ignores entirely when converting to
# PDF — the reason slides were being cut off mid-sentence.
BULLET_SIZES = [26, 24, 22, 20, 18, 16, 14]
CHARS_PER_LINE_AT_24PT = 62.0


def _blank(prs):
    return prs.slides.add_slide(prs.slide_layouts[6])


def _textbox(slide, left, top, width, height):
    box = slide.shapes.add_textbox(left, top, width, height)
    frame = box.text_frame
    frame.word_wrap = True
    frame.margin_left = 0
    frame.margin_right = 0
    frame.margin_top = 0
    frame.margin_bottom = 0
    return frame


def _run(paragraph, text, size, bold=False, color=INK, italic=False):
    run = paragraph.add_run()
    run.text = text
    run.font.size = Pt(size)
    run.font.bold = bold
    run.font.italic = italic
    run.font.name = FONT
    run.font.color.rgb = color
    return run


def _heading(slide, text, accent_rule=True):
    frame = _textbox(slide, MARGIN, HEADING_TOP, BODY_W, HEADING_H)
    frame.vertical_anchor = MSO_ANCHOR.BOTTOM
    para = frame.paragraphs[0]
    # Long headings shrink rather than wrapping into the body.
    size = 34 if len(text) <= 52 else (30 if len(text) <= 74 else 26)
    _run(para, text, size, bold=True)
    if accent_rule:
        bar = slide.shapes.add_shape(1, MARGIN, HEADING_TOP + HEADING_H + Emu(45720), Emu(548640), Emu(45720))
        bar.fill.solid()
        bar.fill.fore_color.rgb = ACCENT
        bar.line.fill.background()
        bar.shadow.inherit = False


def _estimate_lines(text, size, width_frac=1.0):
    """How many wrapped lines this run of text will take at this size."""
    if not text:
        return 1
    per_line = max(12.0, CHARS_PER_LINE_AT_24PT * (24.0 / size) * width_frac)
    return max(1, int(len(text) / per_line) + (1 if len(text) % per_line else 0))


def _fit_size(items, width_frac=1.0, available_h_emu=None):
    """Largest size from BULLET_SIZES at which every bullet fits the body box."""
    available = available_h_emu if available_h_emu is not None else int(BODY_H)
    for size in BULLET_SIZES:
        line_emu = Pt(size * 1.35).emu
        gap_emu = Pt(size * 0.55).emu
        total = 0
        for item in items:
            total += _estimate_lines(item.get("text", ""), size, width_frac) * line_emu + gap_emu
        if total <= available:
            return size
    return BULLET_SIZES[-1]


def _hang(para, size, level):
    """Wrapped lines align under the text, not back at the margin.

    python-pptx exposes no indent API, so this writes marL/indent onto a:pPr
    directly. Without it every bullet that wrapped ran back to the left edge,
    which is the clearest single tell that a deck was generated rather than
    made."""
    indent = int(Pt(size * 0.95).emu)
    left = indent * (level + 1)
    pPr = para._pPr if para._pPr is not None else para._p.get_or_add_pPr()
    pPr.set("marL", str(left))
    pPr.set("indent", str(-indent))


def _bullets(frame, items, size, width_frac=1.0):
    first = True
    for item in items:
        text = (item.get("text") or "").strip()
        if not text:
            continue
        para = frame.paragraphs[0] if first else frame.add_paragraph()
        first = False
        level = min(int(item.get("level") or 0), 4)
        para.level = level
        para.space_after = Pt(size * 0.55)
        _hang(para, size, level)
        marker = "•  " if level == 0 else "–  "
        _run(para, marker, size, color=ACCENT if level == 0 else MUTED)
        # Inline **bold** is kept, because emphasis is most of what a bullet has.
        for chunk, bold in _split_bold(text):
            _run(para, chunk, size, bold=bold, color=INK if level == 0 else MUTED)


def _split_bold(text):
    out = []
    rest = text
    while "**" in rest:
        before, _, after = rest.partition("**")
        if before:
            out.append((before, False))
        bold, sep, remainder = after.partition("**")
        if not sep:
            out.append(("**" + bold, False))
            return out
        out.append((bold, True))
        rest = remainder
    if rest:
        out.append((rest, False))
    return out or [(text, False)]


def _notes(slide, text):
    if not text:
        return
    slide.notes_slide.notes_text_frame.text = text


def slide_title(prs, spec):
    slide = _blank(prs)
    frame = _textbox(slide, MARGIN, Emu(2057400), BODY_W, Emu(1828800))
    frame.vertical_anchor = MSO_ANCHOR.MIDDLE
    para = frame.paragraphs[0]
    heading = spec.get("heading") or "Untitled"
    _run(para, heading, 44 if len(heading) <= 60 else 36, bold=True)
    for line in [spec.get("subtitle"), spec.get("date")]:
        if not line:
            continue
        sub = frame.add_paragraph()
        sub.space_before = Pt(10)
        _run(sub, line, 18, color=MUTED)
    bar = slide.shapes.add_shape(1, MARGIN, Emu(1874520), Emu(1097280), Emu(54864))
    bar.fill.solid()
    bar.fill.fore_color.rgb = ACCENT
    bar.line.fill.background()
    bar.shadow.inherit = False
    return slide


def slide_section(prs, spec):
    slide = _blank(prs)
    frame = _textbox(slide, MARGIN, Emu(2743200), BODY_W, Emu(1371600))
    frame.vertical_anchor = MSO_ANCHOR.MIDDLE
    para = frame.paragraphs[0]
    _run(para, spec.get("heading") or "", 36, bold=True, color=ACCENT)
    return slide


def slide_bullets(prs, spec):
    slide = _blank(prs)
    _heading(slide, spec.get("heading") or "")
    items = spec.get("bullets") or []
    size = _fit_size(items)
    frame = _textbox(slide, MARGIN, BODY_TOP, BODY_W, BODY_H)
    _bullets(frame, items, size)
    _notes(slide, spec.get("notes"))
    return slide


def slide_two(prs, spec):
    slide = _blank(prs)
    _heading(slide, spec.get("heading") or "")
    gutter = Emu(457200)
    col_w = Emu(int((BODY_W - gutter) / 2))
    left_items = spec.get("left") or []
    right_items = spec.get("right") or []
    size = min(_fit_size(left_items, 0.46), _fit_size(right_items, 0.46))
    for index, items in enumerate((left_items, right_items)):
        if not items:
            continue
        left = MARGIN + (col_w + gutter) * index
        frame = _textbox(slide, left, BODY_TOP, col_w, BODY_H)
        _bullets(frame, items, size, width_frac=0.46)
    _notes(slide, spec.get("notes"))
    return slide


def slide_table(prs, spec):
    slide = _blank(prs)
    _heading(slide, spec.get("heading") or "")
    header = spec.get("header") or []
    rows = spec.get("rows") or []
    if not header and not rows:
        return slide
    cols = max(len(header), max((len(r) for r in rows), default=1))
    body_rows = len(rows) + (1 if header else 0)
    height = min(int(BODY_H), Emu(int(365760 * body_rows)))
    shape = slide.shapes.add_table(body_rows, cols, MARGIN, BODY_TOP, BODY_W, height)
    table = shape.table
    # Sized to the row count: eleven rows at one size is unreadable, four is airy.
    size = 16 if body_rows <= 6 else (13 if body_rows <= 9 else 11)

    def write(cell, text, bold, color):
        cell.text = ""
        cell.margin_left = Emu(91440)
        cell.margin_right = Emu(91440)
        cell.margin_top = Emu(45720)
        cell.margin_bottom = Emu(45720)
        cell.vertical_anchor = MSO_ANCHOR.MIDDLE
        para = cell.text_frame.paragraphs[0]
        for chunk, is_bold in _split_bold(text or ""):
            _run(para, chunk, size, bold=bold or is_bold, color=color)

    offset = 0
    if header:
        for c in range(cols):
            cell = table.cell(0, c)
            write(cell, header[c] if c < len(header) else "", True, PAPER)
            cell.fill.solid()
            cell.fill.fore_color.rgb = ACCENT
        offset = 1
    for r, row in enumerate(rows):
        for c in range(cols):
            cell = table.cell(r + offset, c)
            write(cell, row[c] if c < len(row) else "", False, INK)
            cell.fill.solid()
            cell.fill.fore_color.rgb = PAPER if r % 2 == 0 else RGBColor(0xF9, 0xFA, 0xFB)
    _notes(slide, spec.get("notes"))
    return slide


def slide_image(prs, spec):
    """A figure sized to its own aspect ratio, never stretched to a box."""
    slide = _blank(prs)
    heading = spec.get("heading") or ""
    if heading:
        _heading(slide, heading)
        top, avail_h = BODY_TOP, BODY_H
    else:
        top, avail_h = MARGIN, SLIDE_H - MARGIN * 2

    path = spec.get("image")
    caption = (spec.get("caption") or "").strip()
    caption_h = Emu(365760) if caption else Emu(0)
    avail_h = Emu(int(avail_h - caption_h))

    ratio = 1.0
    if Image is not None and path and os.path.exists(path):
        try:
            with Image.open(path) as img:
                if img.height:
                    ratio = img.width / float(img.height)
        except Exception:
            ratio = 1.0

    # Fit inside the box, preserving aspect, then centre it.
    width = int(BODY_W)
    height = int(width / ratio) if ratio else int(avail_h)
    if height > int(avail_h):
        height = int(avail_h)
        width = int(height * ratio)
    left = Emu(int((SLIDE_W - width) / 2))
    if path and os.path.exists(path):
        slide.shapes.add_picture(path, left, Emu(int(top)), Emu(width), Emu(height))

    if caption:
        frame = _textbox(slide, MARGIN, Emu(int(top) + height + 91440), BODY_W, caption_h)
        para = frame.paragraphs[0]
        para.alignment = PP_ALIGN.CENTER
        _run(para, caption, 14, color=MUTED, italic=True)
    _notes(slide, spec.get("notes"))
    return slide


def slide_compare(prs, spec):
    """Two labelled columns on tinted cards — the layout a differential, a
    mild-versus-severe or a before-and-after actually wants, and the one
    markdown had no way to ask for."""
    slide = _blank(prs)
    _heading(slide, spec.get("heading") or "")
    gutter = Emu(365760)
    col_w = Emu(int((BODY_W - gutter) / 2))
    columns = (spec.get("columns") or [])[:2]
    tints = [RGBColor(0xEF, 0xF6, 0xFF), RGBColor(0xFE, 0xF3, 0xC7)]
    edges = [ACCENT, RGBColor(0xD9, 0x77, 0x06)]
    sizes = [_fit_size(c.get("bullets") or [], 0.44, int(BODY_H) - int(Emu(548640)))
             for c in columns] or [BULLET_SIZES[0]]
    size = min(sizes)
    for index, column in enumerate(columns):
        left = MARGIN + (col_w + gutter) * index
        card = slide.shapes.add_shape(5, left, BODY_TOP, col_w, BODY_H)   # rounded rect
        card.fill.solid()
        card.fill.fore_color.rgb = tints[index % 2]
        card.line.color.rgb = edges[index % 2]
        card.line.width = Pt(1)
        card.shadow.inherit = False
        card.text_frame.text = ""

        label = _textbox(slide, left + Emu(228600), BODY_TOP + Emu(182880),
                         Emu(int(col_w) - 457200), Emu(365760))
        _run(label.paragraphs[0], (column.get("label") or "").upper(), 14,
             bold=True, color=edges[index % 2])

        frame = _textbox(slide, left + Emu(228600), BODY_TOP + Emu(640080),
                         Emu(int(col_w) - 457200), Emu(int(BODY_H) - 822960))
        _bullets(frame, column.get("bullets") or [], size, width_frac=0.44)
    _notes(slide, spec.get("notes"))
    return slide


def slide_callout(prs, spec):
    """One thing worth stopping on: a red flag, a dose, a rule of thumb."""
    slide = _blank(prs)
    _heading(slide, spec.get("heading") or "")
    card = slide.shapes.add_shape(5, MARGIN, BODY_TOP, BODY_W, Emu(int(BODY_H * 0.62)))
    card.fill.solid()
    card.fill.fore_color.rgb = RGBColor(0xFE, 0xF3, 0xC7)
    card.line.color.rgb = RGBColor(0xD9, 0x77, 0x06)
    card.line.width = Pt(1.5)
    card.shadow.inherit = False
    card.text_frame.text = ""

    text = (spec.get("text") or "").strip()
    frame = _textbox(slide, MARGIN + Emu(457200), BODY_TOP + Emu(365760),
                     Emu(int(BODY_W) - 914400), Emu(int(BODY_H * 0.62) - 731520))
    frame.vertical_anchor = MSO_ANCHOR.MIDDLE
    para = frame.paragraphs[0]
    para.alignment = PP_ALIGN.CENTER
    size = 28 if len(text) <= 90 else (22 if len(text) <= 180 else 18)
    for chunk, bold in _split_bold(text):
        _run(para, chunk, size, bold=bold or True, color=RGBColor(0x78, 0x35, 0x0F))
    _notes(slide, spec.get("notes"))
    return slide


def slide_figure(prs, spec):
    """A figure beside its text, rather than alone on a slide of its own."""
    slide = _blank(prs)
    _heading(slide, spec.get("heading") or "")
    gutter = Emu(365760)
    text_w = Emu(int((BODY_W - gutter) * 0.46))
    img_w = Emu(int((BODY_W - gutter) * 0.54))

    items = spec.get("bullets") or []
    size = _fit_size(items, 0.42)
    frame = _textbox(slide, MARGIN, BODY_TOP, text_w, BODY_H)
    _bullets(frame, items, size, width_frac=0.42)

    path = spec.get("image")
    if path and os.path.exists(path):
        ratio = 1.0
        if Image is not None:
            try:
                with Image.open(path) as img:
                    if img.height:
                        ratio = img.width / float(img.height)
            except Exception:
                ratio = 1.0
        width = int(img_w)
        height = int(width / ratio) if ratio else int(BODY_H)
        if height > int(BODY_H):
            height = int(BODY_H)
            width = int(height * ratio)
        left = MARGIN + text_w + gutter + Emu(int((int(img_w) - width) / 2))
        top = BODY_TOP + Emu(int((int(BODY_H) - height) / 2))
        slide.shapes.add_picture(path, left, top, Emu(width), Emu(height))
    _notes(slide, spec.get("notes"))
    return slide


BUILDERS = {
    "title": slide_title,
    "section": slide_section,
    "bullets": slide_bullets,
    "two": slide_two,
    "table": slide_table,
    "image": slide_image,
    "compare": slide_compare,
    "callout": slide_callout,
    "figure": slide_figure,
}


def main():
    if len(sys.argv) < 2:
        print("usage: render_pptx.py <output.pptx>  (spec on stdin)", file=sys.stderr)
        return 2
    spec = json.load(sys.stdin)

    prs = Presentation()
    prs.slide_width = SLIDE_W
    prs.slide_height = SLIDE_H

    slides = spec.get("slides") or []
    if not slides:
        print("spec contains no slides", file=sys.stderr)
        return 3

    for item in slides:
        BUILDERS.get(item.get("type") or "bullets", slide_bullets)(prs, item)

    prs.save(sys.argv[1])
    return 0


if __name__ == "__main__":
    sys.exit(main())