Files
Bkk1234 4f74a509d5 intro-irre: แปลงตำราวิศวกรรมชลประทานเบื้องต้นเป็นเว็บเอกสาร 10 บท
- tools/extract.py: PDF 300 หน้า -> extracted/pages.json + crop ภาพ/ตาราง/สมการ 423 รูป
  (ถอด PUA วรรณยุกต์ไทย, รวมสระอำ, แยกหัวข้อที่ระดับ span)
- tools/build.py: generator หน้า docs แบบ static (สารบัญซ้าย/เนื้อหา/ในหน้านี้)
- index.html + chapters/ch01..10.html + css/docs.css + js/docs.js
  (ธีม K2D, ค้นหาเต็มเล่มผ่าน data/search.json, dark mode, drawer มือถือ)
- README.md: วิธี build และข้อจำกัดที่รู้อยู่
2026-11-19 01:34:49 +07:00

505 lines
23 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""Build the static documentation site from extracted/pages.json.
python tools/build.py
Produces
index.html cover + chapter grid
chapters/chNN.html one page per chapter (sections as anchors)
data/nav.json chapter/section tree used by search + sidebar
data/search.json full-text search index (section level)
assets/cover.jpg book cover rendered from page 1
"""
from __future__ import annotations
import html
import json
import re
import shutil
from pathlib import Path
import pymupdf as fitz
ROOT = Path(__file__).resolve().parent.parent
SRC = ROOT / "extracted" / "pages.json"
PDF = Path(r"C:\Users\BANK\Downloads\Documents\Intro-Irri-Eng.pdf")
CHAPTER_DIR = ROOT / "chapters"
BOOK_TITLE = "วิศวกรรมชลประทานเบื้องต้น"
BOOK_SUBTITLE = "Introduction to Irrigation Engineering"
COURSE_CODE = "02207211"
BOOK_AUTHOR = "ภาควิชาวิศวกรรมชลประทาน มหาวิทยาลัยเกษตรศาสตร์"
BOOK_EDITION = "พิมพ์ครั้งที่ 10 · พ.ศ. 2558"
# --------------------------------------------------------------------- utils
def esc(text: str) -> str:
return html.escape(text, quote=False)
def clean(text: str) -> str:
text = (text or "").replace("\u2022", "•").replace("\n", " ")
text = re.sub(r"\s+", " ", text).strip()
# "2.7การหา…" -> "2.7 การหา…" (some chapters lost the space after the number)
text = re.sub(r"^(\d+(?:\.\d+)*)(?=[^\d\s.])", r"\1 ", text)
return text
def slug_section(index: int, title: str) -> str:
m = re.match(r"^(\d+(?:\.\d+)*)\.?\s", title)
if m:
return "s" + m.group(1).replace(".", "-")
return f"sec-{index}"
def is_noise(item) -> bool:
if item["type"] != "p":
return False
t = clean(item.get("text", ""))
if len(t) < 3:
return True
if re.fullmatch(r"[\d\s.\-–]+", t):
return True
return False
# ----------------------------------------------------------------- structure
def toc_titles(data):
"""Chapter titles as printed in the book's own table of contents."""
titles = {}
for page in data["pages"][:8]:
for it in page["items"]:
if it["type"] not in ("p", "h2", "h3", "h1"):
continue
text = clean(it.get("text", ""))
m = re.match(r"^บทที่\s*(\d+)\s*(.+)$", text)
if not m:
continue
body = m.group(2).strip()
if len(body) < 3 or re.fullmatch(r"[\d.]+", body):
continue
titles.setdefault(int(m.group(1)), body)
return titles
def load_payload():
data = json.loads(SRC.read_text(encoding="utf-8"))
chapters = []
bookmarks = [t for t in data["toc"] if t["level"] == 2 and t["page"] > 0]
bookmarks.sort(key=lambda t: t["page"])
starts = [t["page"] for t in bookmarks]
for idx, bm in enumerate(bookmarks):
start = bm["page"]
end = starts[idx + 1] if idx + 1 < len(bookmarks) else data["page_count"] + 1
pages = [p for p in data["pages"] if start <= p["page"] < end]
chapters.append(build_chapter(idx + 1, pages, start, end - 1))
printed = toc_titles(data)
for ch in chapters:
extra = printed.get(ch["number"], "")
if extra and len(extra) > len(re.sub(r"^บทที่\s*\d+\s*", "", ch["title"])):
ch["title"] = f'บทที่ {ch["number"]} {extra}'
return data, chapters
def build_chapter(number, pages, page_start, page_end):
title_parts, sections, current = [], [], None
items = [it for p in pages for it in p["items"]]
# chapter title = leading h1/p run before the first numbered section
for it in items:
if it["type"] == "h1":
title_parts.append(clean(it["text"]))
continue
if it["type"] == "p" and len(title_parts) < 3 and not sections \
and not re.match(r"^\d", clean(it.get("text", ""))):
title_parts.append(clean(it["text"]))
continue
break
rest = items[len(title_parts):]
sec_no = 0
for it in rest:
t = it["type"]
if t in ("h2", "h1"):
sec_no += 1
current = {
"id": slug_section(sec_no, clean(it["text"])),
"title": clean(it["text"]),
"page": it.get("page", page_start),
"items": [],
}
sections.append(current)
continue
if t == "h3":
if current is None:
sec_no += 1
current = {"id": f"sec-{sec_no}", "title": "บทนำ", "page": it.get("page", page_start), "items": []}
sections.append(current)
current["items"].append({"type": "h3", "text": clean(it["text"]),
"id": f'{current["id"]}-h{sum(1 for x in current["items"] if x["type"] == "h3") + 1}'})
continue
if t == "caption":
continue
if t == "figure":
if current is None:
sec_no += 1
current = {"id": f"sec-{sec_no}", "title": "ภาพประกอบ", "page": it.get("page", page_start), "items": []}
sections.append(current)
current["items"].append({
"type": "figure",
"src": "../../../" if False else it["src"],
"width": it.get("width", 800),
"height": it.get("height", 600),
"caption": clean(it.get("caption", "")),
})
continue
if is_noise(it):
continue
if current is None:
sec_no += 1
current = {"id": f"sec-{sec_no}", "title": "บทนำ", "page": it.get("page", page_start), "items": []}
sections.append(current)
current["items"].append({"type": "p", "text": clean(it["text"])})
title = " ".join(dict.fromkeys(title_parts)) or f"บทที่ {number}"
if not title.startswith("บทที่"):
title = f"บทที่ {number} {title}"
# tidy: a stray "บทที่ N" line or a figure-only prologue is not a section
cleaned = []
for sec in sections:
if re.fullmatch(r"บทที่\s*\d+", sec["title"]):
if cleaned:
cleaned[-1]["items"].extend(sec["items"])
continue
if sec["title"] == "ภาพประกอบ" and not cleaned:
sec["title"] = "บทนำ"
cleaned.append(sec)
sections = cleaned
for i, sec in enumerate(sections):
if not sec["title"]:
sec["title"] = f"หัวข้อ {i + 1}"
num = number
return {
"number": num,
"slug": f"ch{num:02d}",
"href": f"chapters/ch{num:02d}.html",
"title": title,
"page_start": page_start,
"page_end": page_end,
"sections": sections,
}
# ---------------------------------------------------------------------- html
def section_html(sec):
out = [f'<section class="doc-section" id="{sec["id"]}">',
f' <h2><a class="anchor" href="#{sec["id"]}">{esc(sec["title"])}</a>'
f'<span class="page-ref" title="หน้าในหนังสือ">น. {sec["page"]}</span></h2>']
for it in sec["items"]:
if it["type"] == "h3":
hid = it.get("id", "")
idattr = f' id="{hid}"' if hid else ""
out.append(f' <h3{idattr}>{esc(it["text"])}</h3>')
elif it["type"] == "p":
out.append(f' <p>{inline(it["text"])}</p>')
elif it["type"] == "figure":
cap = it["caption"]
out.append(' <figure>')
out.append(f' <img src="../{it["src"]}" width="{it["width"]}" height="{it["height"]}" '
f'loading="lazy" alt="{esc(cap or "ภาพประกอบ")}">')
if cap:
out.append(f' <figcaption>{esc(cap)}</figcaption>')
out.append(' </figure>')
out.append('</section>')
return "\n".join(out)
def inline(text: str) -> str:
"""Escape, then turn bullet runs into list markup."""
t = esc(text)
if t.startswith("• ") or t.startswith("- "):
return f'<span class="bullet">{t}</span>'
return t
def chapter_body(ch):
parts = []
for sec in ch["sections"]:
parts.append(section_html(sec))
return "\n".join(parts)
def toc_html(chapters, current=None):
out = ['<nav class="side-nav" aria-label="สารบัญ">']
for ch in chapters:
open_ = " open" if current and current["number"] == ch["number"] else ""
active = " is-active" if current and current["number"] == ch["number"] else ""
label = esc(re.sub(r"^บทที่\s*\d+\s*", "", ch["title"]))
out.append(f'<details class="nav-group{active}"{open_}>')
out.append(f' <summary><span class="nav-num">บทที่ {ch["number"]}</span>'
f'<span class="nav-title">{label}</span></summary>')
out.append(' <ul>')
for sec in ch["sections"]:
sec_active = ""
out.append(f' <li><a class="nav-link{sec_active}" href="../{ch["href"]}#{sec["id"]}">'
f'{esc(sec["title"])}</a></li>')
out.append(' </ul>')
out.append('</details>')
out.append('</nav>')
return "\n".join(out)
HEAD = """<!DOCTYPE html>
<html lang="th">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>{title}</title>
<meta name="description" content="{desc}">
<meta name="theme-color" content="#1e3a8a">
<link rel="icon" href="{root}assets/favicon.svg" type="image/svg+xml">
<link rel="stylesheet" href="{root}css/docs.css">
</head>
<body data-root="{root}">
<a class="skip" href="#main">ข้ามไปที่เนื้อหา</a>
<header class="topbar">
<button class="icon-btn only-mobile" id="navToggle" aria-label="เปิดสารบัญ" aria-expanded="false">
<svg viewBox="0 0 24 24" width="20" height="20" aria-hidden="true"><path d="M3 6h18M3 12h18M3 18h18" stroke="currentColor" stroke-width="2" stroke-linecap="round" fill="none"/></svg>
</button>
<a class="brand" href="{root}index.html">
<svg class="brand-mark" viewBox="0 0 24 24" width="22" height="22" aria-hidden="true">
<path d="M12 2.5c3.6 4.4 6.5 8 6.5 11.2A6.5 6.5 0 0 1 5.5 13.7C5.5 10.5 8.4 6.9 12 2.5Z" fill="none" stroke="currentColor" stroke-width="1.7" stroke-linejoin="round"/>
<path d="M9 14.4c1.6-1.2 3.4-1.2 5 0" fill="none" stroke="currentColor" stroke-width="1.4" stroke-linecap="round"/>
</svg>
<span class="brand-text"><strong>วิศวกรรมชลประทานเบื้องต้น</strong><small>02207211</small></span>
</a>
<div class="topbar-actions">
<button class="search-btn" id="searchOpen" aria-label="ค้นหาในตำรา">
<svg viewBox="0 0 24 24" width="16" height="16" aria-hidden="true"><circle cx="11" cy="11" r="6.5" fill="none" stroke="currentColor" stroke-width="2"/><path d="m16 16 4.5 4.5" stroke="currentColor" stroke-width="2" stroke-linecap="round"/></svg>
<span>ค้นหา</span><kbd>Ctrl K</kbd>
</button>
<button class="icon-btn" id="themeToggle" aria-label="สลับโหมดสว่าง/มืด" aria-pressed="false">
<svg class="i-sun" viewBox="0 0 24 24" width="18" height="18" aria-hidden="true"><circle cx="12" cy="12" r="4.2" fill="none" stroke="currentColor" stroke-width="1.8"/><path d="M12 2.6v2.2M12 19.2v2.2M2.6 12h2.2M19.2 12h2.2M5.4 5.4l1.6 1.6M17 17l1.6 1.6M18.6 5.4 17 7M7 17l-1.6 1.6" stroke="currentColor" stroke-width="1.8" stroke-linecap="round"/></svg>
<svg class="i-moon" viewBox="0 0 24 24" width="18" height="18" aria-hidden="true"><path d="M20 14.5A8.2 8.2 0 0 1 9.5 4a8.4 8.4 0 1 0 10.5 10.5Z" fill="none" stroke="currentColor" stroke-width="1.8" stroke-linejoin="round"/></svg>
</button>
</div>
</header>
"""
FOOT = """
<div class="scrim" id="scrim" hidden></div>
<div class="search-modal" id="searchModal" role="dialog" aria-modal="true" aria-labelledby="searchTitle" hidden>
<div class="search-head">
<h2 id="searchTitle" class="sr">ค้นหา</h2>
<svg viewBox="0 0 24 24" width="18" height="18" aria-hidden="true"><circle cx="11" cy="11" r="6.5" fill="none" stroke="currentColor" stroke-width="2"/><path d="m16 16 4.5 4.5" stroke="currentColor" stroke-width="2" stroke-linecap="round"/></svg>
<input id="searchInput" type="search" placeholder="พิมพ์คำค้น เช่น ความชื้น, ประสิทธิภาพการชลประทาน" autocomplete="off" aria-label="คำค้น">
<button class="icon-btn" id="searchClose" aria-label="ปิด"><svg viewBox="0 0 24 24" width="18" height="18" aria-hidden="true"><path d="M6 6l12 12M18 6 6 18" stroke="currentColor" stroke-width="2" stroke-linecap="round"/></svg></button>
</div>
<div class="search-results" id="searchResults"><p class="search-hint">พิมพ์อย่างน้อย 2 ตัวอักษร · ค้นทั้งเล่ม 10 บท</p></div>
</div>
<script src="{root}js/docs.js" defer></script>
</body>
</html>
"""
def page_shell(title, desc, root, body, aside=""):
return HEAD.format(title=esc(title), desc=esc(desc), root=root) + body + aside + FOOT.format(root=root)
def build_chapter_page(ch, chapters, prev_ch, next_ch):
aside = ['<aside class="page-toc" aria-label="ในหน้านี้"><p class="page-toc-label">ในหน้านี้</p><ul>']
for sec in ch["sections"]:
aside.append(f' <li><a href="#{sec["id"]}">{esc(sec["title"])}</a></li>')
for it in sec["items"]:
if it["type"] == "h3":
hid = it.get("id") or sec["id"]
aside.append(f' <li class="sub"><a href="#{hid}">{esc(it["text"])}</a></li>')
aside.append('</ul></aside>')
pager = ['<nav class="pager" aria-label="บทก่อนหน้า/ถัดไป">']
if prev_ch:
pager.append(f'<a class="pager-link" href="{prev_ch["slug"]}.html"><span>← บทก่อนหน้า</span>'
f'<strong>{esc(prev_ch["title"])}</strong></a>')
if next_ch:
pager.append(f'<a class="pager-link next" href="{next_ch["slug"]}.html"><span>บทถัดไป →</span>'
f'<strong>{esc(next_ch["title"])}</strong></a>')
pager.append('</nav>')
body = f"""
<div class="layout">
<div class="side" id="side">{toc_html(chapters, ch)}</div>
<main id="main" class="main">
<article class="doc">
<p class="breadcrumb"><a href="../index.html">หน้าปกตำรา</a><span>/</span>บทที่ {ch["number"]}</p>
<h1 class="doc-title">{esc(ch["title"])}</h1>
<p class="doc-meta">หน้า {ch["page_start"]}–{ch["page_end"]} ในหนังสือ · {len(ch["sections"])} หัวข้อ</p>
{chapter_body(ch)}
{''.join(pager)}
</article>
</main>
{''.join(aside)}
</div>
"""
title = f'{ch["title"]} · {BOOK_TITLE}'
return page_shell(title, ch["title"], "../", body)
def build_index(chapters):
total_sec = sum(len(c["sections"]) for c in chapters)
total_fig = sum(1 for c in chapters for s in c["sections"] for i in s["items"] if i["type"] == "figure")
cards = []
for ch in chapters:
card_title = re.sub(r"^บทที่\s*\d+\s*", "", ch["title"])
cards.append(f"""
<li class="chapter-card">
<a href="{ch["href"]}">
<span class="card-num">บทที่ {ch["number"]}</span>
<span class="card-title">{esc(card_title)}</span>
<span class="card-meta">{len(ch["sections"])} หัวข้อ · หน้า {ch["page_start"]}–{ch["page_end"]}</span>
<span class="card-cta">อ่านบทนี้
<svg viewBox="0 0 24 24" width="16" height="16" aria-hidden="true"><path d="M5 12h13M13 6l6 6-6 6" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"/></svg>
</span>
</a>
</li>""")
body = f"""
<main id="main" class="home">
<section class="hero">
<div class="hero-copy">
<p class="eyebrow">ตำราออนไลน์ · {COURSE_CODE}</p>
<h1>{BOOK_TITLE}</h1>
<p class="hero-sub">{BOOK_SUBTITLE}</p>
<p class="hero-lead">เรียบเรียงเนื้อหาครบทั้ง {len(chapters)} บท จากต้นฉบับ {BOOK_TITLE} {BOOK_EDITION}
แปลงเป็นเว็บเอกสารที่ค้นหาได้ทุกย่อหน้า เลือกคัดลอกข้อความได้ และเปิดอ่านได้ทุกขนาดหน้าจอ</p>
<div class="hero-actions">
<a class="btn primary" href="chapters/{chapters[0]["slug"]}.html">เริ่มอ่านบทที่ 1</a>
<button class="btn ghost" id="searchOpenHero">ค้นหาคำในตำรา</button>
</div>
<dl class="stats">
<div><dt>บท</dt><dd>{len(chapters)}</dd></div>
<div><dt>หัวข้อ</dt><dd>{total_sec}</dd></div>
<div><dt>ภาพและตาราง</dt><dd>{total_fig}</dd></div>
</dl>
</div>
<figure class="hero-cover">
<img src="assets/cover.jpg" width="640" height="906" alt="หน้าปกตำรา {BOOK_TITLE}" loading="eager">
<figcaption>{BOOK_AUTHOR}</figcaption>
</figure>
</section>
<section class="chapters">
<h2>สารบัญ</h2>
<ul class="chapter-grid">{''.join(cards)}
</ul>
</section>
<section class="about">
<h2>เกี่ยวกับตำราเล่มนี้</h2>
<div class="about-grid">
<div>
<h3>เนื้อหา</h3>
<p>ครอบคลุมตั้งแต่ความหมายและขอบเขตงานวิศวกรรมชลประทาน ความสัมพันธ์ระหว่างดิน–น้ำ–พืช
ความต้องการน้ำของพืช การกำหนดการให้น้ำ วิธีการให้น้ำ การส่งน้ำ การระบายน้ำ
การควบคุมการส่งน้ำ ไปจนถึงพื้นฐานการออกแบบคลองส่งน้ำ</p>
</div>
<div>
<h3>รูปแบบเอกสาร</h3>
<p>ทุกหัวข้อมีเลขหน้าอ้างอิงถึงต้นฉบับ ภาพประกอบและสมการคงรูปแบบเดิมจากหนังสือ
ส่วนเนื้อความถูกแปลงเป็นข้อความจริงสำหรับการค้นหาและคัดลอก</p>
</div>
<div>
<h3>การใช้งาน</h3>
<p>กด <kbd>Ctrl</kbd> + <kbd>K</kbd> เพื่อค้นหาทั้งเล่ม ใช้สารบัญด้านซ้ายเพื่อข้ามบท
และสารบัญด้านขวาสำหรับข้ามหัวข้อภายในบทนั้น</p>
</div>
</div>
</section>
<footer class="home-foot">
<p>{BOOK_AUTHOR} · {BOOK_EDITION}</p>
<p>เอกสารอิเล็กทรอนิกส์เพื่อการเรียนการสอน · แปลงจากต้นฉบับ PDF</p>
</footer>
</main>
"""
return page_shell(f"{BOOK_TITLE} · {BOOK_SUBTITLE}", "ตำราออนไลน์ วิศวกรรมชลประทานเบื้องต้น 10 บท", "", body)
# --------------------------------------------------------------------- assets
def write_search(chapters, data_size):
entries = []
for ch in chapters:
for sec in ch["sections"]:
for it in sec["items"]:
if it["type"] != "p":
continue
entries.append({
"u": f'{ch["href"]}#{sec["id"]}',
"c": f'บทที่ {ch["number"]}',
"s": sec["title"],
"p": sec["page"],
"x": it["text"][:260],
})
out = ROOT / "data" / "search.json"
out.parent.mkdir(parents=True, exist_ok=True)
out.write_text(json.dumps(entries, ensure_ascii=False), encoding="utf-8")
return len(entries)
def write_nav(chapters):
tree = [{"n": c["number"], "t": c["title"], "u": c["href"],
"s": [{"t": s["title"], "u": f'{c["href"]}#{s["id"]}'} for s in c["sections"]]}
for c in chapters]
out = ROOT / "data" / "nav.json"
out.parent.mkdir(parents=True, exist_ok=True)
out.write_text(json.dumps(tree, ensure_ascii=False, indent=1), encoding="utf-8")
def write_cover():
if not PDF.exists():
return
doc = fitz.open(PDF)
page = doc[0]
rect = page.rect
zoom = 640 / rect.width
pix = page.get_pixmap(matrix=fitz.Matrix(zoom, zoom))
path = ROOT / "assets" / "cover.jpg"
path.parent.mkdir(parents=True, exist_ok=True)
pix.save(str(path), jpg_quality=88)
def write_favicon():
svg = ('<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24">'
'<rect width="24" height="24" rx="6" fill="#1e3a8a"/>'
'<path d="M12 4.5c3 3.7 5.4 6.7 5.4 9.3a5.4 5.4 0 0 1-10.8 0c0-2.6 2.4-5.6 5.4-9.3Z" '
'fill="none" stroke="#fff" stroke-width="1.6" stroke-linejoin="round"/></svg>')
(ROOT / "assets").mkdir(parents=True, exist_ok=True)
(ROOT / "assets" / "favicon.svg").write_text(svg, encoding="utf-8")
def main():
data, chapters = load_payload()
CHAPTER_DIR.mkdir(exist_ok=True)
for i, ch in enumerate(chapters):
prev_ch = chapters[i - 1] if i > 0 else None
next_ch = chapters[i + 1] if i + 1 < len(chapters) else None
html_text = build_chapter_page(ch, chapters, prev_ch, next_ch)
(CHAPTER_DIR / f'{ch["slug"]}.html').write_text(html_text, encoding="utf-8")
(ROOT / "index.html").write_text(build_index(chapters), encoding="utf-8")
write_nav(chapters)
n = write_search(chapters, data["page_count"])
write_cover()
write_favicon()
total_p = sum(1 for c in chapters for s in c["sections"] for i in s["items"] if i["type"] == "p")
total_f = sum(1 for c in chapters for s in c["sections"] for i in s["items"] if i["type"] == "figure")
print(f"chapters={len(chapters)} sections={sum(len(c['sections']) for c in chapters)} "
f"paragraphs={total_p} figures={total_f} search_entries={n}")
if __name__ == "__main__":
main()