# pip install cairosvg pillow imagehash scikit-image uharfbuzz freetype-py
import io, json, tarfile, base64, math
from PIL import Image, ImageOps, ImageDraw, ImageFont
import imagehash
from skimage.metrics import structural_similarity as ssim
import cairosvg

CANVAS = (512, 512)
BGCOLOR = 255  # white
FGCOLOR = 0    # black

# --- SVG -> raster ---
def rasterize_svg_path(path_d: str, canvas=CANVAS) -> Image.Image:
# Build a minimal SVG document; rely on CAIRO for correct path handling
svg = f'''<svg xmlns="http://www.w3.org/2000/svg" width="{canvas[0]}" height="{canvas[1]}" viewBox="0 0 2048 2048">
<rect width="100%" height="100%" fill="white"/>
<path d="{path_d}" fill="black" fill-rule="nonzero"/>
</svg>'''
png_bytes = cairosvg.svg2png(bytestring=svg.encode('utf-8'))
img = Image.open(io.BytesIO(png_bytes)).convert('L')
return img

# --- Perceptual hash ---
def phash_img(img: Image.Image) -> str:
# Normalize to grayscale and fixed size
img = ImageOps.grayscale(img).resize((128, 128), Image.LANCZOS)
return str(imagehash.phash(img))

# --- Reference atlas from TTF ---
def render_char(candidate: str, ttf_path: str, canvas=CANVAS, size=420) -> Image.Image:
# Render centered text on same canvas to approximate glyph shapes
font = ImageFont.truetype(ttf_path, size=size)
img = Image.new('L', canvas, color=BGCOLOR)
draw = ImageDraw.Draw(img)
w, h = draw.textbbox((0,0), candidate, font=font)[2:]
dx = (canvas[0]-w)//2
dy = (canvas[1]-h)//2
draw.text((dx, dy), candidate, fill=FGCOLOR, font=font)
return img

# --- Build atlases for variants ---
FONT_VARIANTS = {
'normal':   '/path/to/Bookerly-Regular.ttf',
'italic':   '/path/to/Bookerly-Italic.ttf',
'bold':     '/path/to/Bookerly-Bold.ttf',
'bolditalic':'/path/to/Bookerly-BoldItalic.ttf',
}
CANDIDATES = [
*[chr(c) for c in range(0x20, 0x7F)],  # basic ASCII
'–', '—', '“', '”', '‘', '’', '•',      # common punctuation
'ff','fi','fl','ffi','ffl'              # ligatures
]

def build_atlases():
atlases = {}  # variant -> list[(char, img)]
for variant, ttf in FONT_VARIANTS.items():
out = []
for ch in CANDIDATES:
img = render_char(ch, ttf)
out.append((ch, img))
atlases[variant] = out
return atlases

# --- SSIM match ---

def best_match(img: Image.Image, atlases) -> tuple[str, float, str]:
# Returns (char, score, variant)
img_n = ImageOps.grayscale(img).resize((128,128), Image.LANCZOS)
img_n = ImageOps.autocontrast(img_n)
best = ('', -1.0, '')
import numpy as np
candA = np.array(img_n)
for variant, entries in atlases.items():
for ch, ref in entries:
ref_n = ImageOps.grayscale(ref).resize((128,128), Image.LANCZOS)
ref_n = ImageOps.autocontrast(ref_n)
candB = np.array(ref_n)
score = ssim(candA, candB)
if score > best[1]:
best = (ch, score, variant)
return best

# --- Putting it together for one TAR batch ---

def process_tar(tar_path: str, cache: dict, atlases) -> list[dict]:
# cache: perceptual-hash -> mapping {char, score, variant}
out_runs = []
with tarfile.open(tar_path, 'r:*') as tf:
glyphs = json.load(tf.extractfile('glyphs.json'))
# page_data_0_4.json may differ in name; list members to find it
pd_name = next(m.name for m in tf.getmembers() if m.name.startswith('page_data_'))
page_data = json.load(tf.extractfile(pd_name))

# 1. Rasterize + hash all glyphs for this batch
id2hash = {}
for gid, meta in glyphs.items():
img = rasterize_svg_path(meta['path'])
h = phash_img(img)
id2hash[int(gid)] = (h, img)

# 2. Ensure all hashes are resolved to characters in cache
for h, img in {v[0]: v[1] for v in id2hash.values()}.items():
if h not in cache:
ch, score, variant = best_match(img, atlases)
cache[h] = { 'char': ch, 'score': float(score), 'variant': variant }

# 3. Decode text runs
for run in page_data:
if run.get('type') != 'TextRun':
continue
decoded = []
for gid in run['glyphs']:
h, _ = id2hash[gid]
decoded.append(cache[h]['char'])
run_out = {
'text': ''.join(decoded),
'rect': run.get('rect'),
'fontStyle': run.get('fontStyle'),
'fontWeight': run.get('fontWeight'),
'fontSize': run.get('fontSize'),
}
out_runs.append(run_out)
return out_runs

# Usage sketch:
# atlases = build_atlases()
# cache = {}
# for tar in sorted(glob('batches/*.tar')):
#     runs = process_tar(tar, cache, atlases)
#     # accumulate runs for layout reconstruction → EPUB/HTML