textflowkit 0.1.3__py3-none-any.whl

textflowkit/render/fonts/OFL-NotoSansSC.txt

@@ -0,0 +1,93 @@
+Copyright 2014-2021 Adobe (http://www.adobe.com/), with Reserved Font Name 'Source'
+
+This Font Software is licensed under the SIL Open Font License, Version 1.1.
+This license is copied below, and is also available with a FAQ at:
+https://scripts.sil.org/OFL
+
+
+-----------------------------------------------------------
+SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007
+-----------------------------------------------------------
+
+PREAMBLE
+The goals of the Open Font License (OFL) are to stimulate worldwide
+development of collaborative font projects, to support the font creation
+efforts of academic and linguistic communities, and to provide a free and
+open framework in which fonts may be shared and improved in partnership
+with others.
+
+The OFL allows the licensed fonts to be used, studied, modified and
+redistributed freely as long as they are not sold by themselves. The
+fonts, including any derivative works, can be bundled, embedded,
+redistributed and/or sold with any software provided that any reserved
+names are not used by derivative works. The fonts and derivatives,
+however, cannot be released under any other type of license. The
+requirement for fonts to remain under this license does not apply
+to any document created using the fonts or their derivatives.
+
+DEFINITIONS
+"Font Software" refers to the set of files released by the Copyright
+Holder(s) under this license and clearly marked as such. This may
+include source files, build scripts and documentation.
+
+"Reserved Font Name" refers to any names specified as such after the
+copyright statement(s).
+
+"Original Version" refers to the collection of Font Software components as
+distributed by the Copyright Holder(s).
+
+"Modified Version" refers to any derivative made by adding to, deleting,
+or substituting -- in part or in whole -- any of the components of the
+Original Version, by changing formats or by porting the Font Software to a
+new environment.
+
+"Author" refers to any designer, engineer, programmer, technical
+writer or other person who contributed to the Font Software.
+
+PERMISSION & CONDITIONS
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of the Font Software, to use, study, copy, merge, embed, modify,
+redistribute, and sell modified and unmodified copies of the Font
+Software, subject to the following conditions:
+
+1) Neither the Font Software nor any of its individual components,
+in Original or Modified Versions, may be sold by itself.
+
+2) Original or Modified Versions of the Font Software may be bundled,
+redistributed and/or sold with any software, provided that each copy
+contains the above copyright notice and this license. These can be
+included either as stand-alone text files, human-readable headers or
+in the appropriate machine-readable metadata fields within text or
+binary files as long as those fields can be easily viewed by the user.
+
+3) No Modified Version of the Font Software may use the Reserved Font
+Name(s) unless explicit written permission is granted by the corresponding
+Copyright Holder. This restriction only applies to the primary font name as
+presented to the users.
+
+4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font
+Software shall not be used to promote, endorse or advertise any
+Modified Version, except to acknowledge the contribution(s) of the
+Copyright Holder(s) and the Author(s) or with their explicit written
+permission.
+
+5) The Font Software, modified or unmodified, in part or in whole,
+must be distributed entirely under this license, and must not be
+distributed under any other license. The requirement for fonts to
+remain under this license does not apply to any document created
+using the Font Software.
+
+TERMINATION
+This license becomes null and void if any of the above conditions are
+not met.
+
+DISCLAIMER
+THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT
+OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE
+COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL
+DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM
+OTHER DEALINGS IN THE FONT SOFTWARE.

textflowkit/render/fonts/README.md

@@ -0,0 +1,19 @@
+Bundled PDF fonts (SIL Open Font License 1.1)
+================================================
+
+The fonts are embedded into generated PDFs by ReportLab. They are included in
+the wheel so Unicode export does not depend on host-installed fonts.
+
+* `NotoSans.ttf`: Noto Sans Regular, from
+  https://github.com/notofonts/noto-fonts/tree/main/hinted/ttf/NotoSans
+  SHA-256 `b85c38ecea8a7cfb39c24e395a4007474fa5a4fc864f6ee33309eb4948d232d5`
+* `NotoSansArabic.ttf`: Noto Sans Arabic Regular, from
+  https://github.com/notofonts/noto-fonts/tree/main/hinted/ttf/NotoSansArabic
+  SHA-256 `ceea25b464a656dc3b26849bab9356740401af62aedf1bfa8b7f0d9b75925b1b`
+* `NotoSansSC.ttf`: Noto Sans SC variable TrueType, from
+  https://github.com/google/fonts/tree/main/ofl/notosanssc
+  SHA-256 `a3041811a78c361b1de50f953c805e0244951c21c5bd412f7232ef0d899af0da`
+
+`OFL-NotoSans.txt` covers the first two fonts. `OFL-NotoSansSC.txt` covers
+Noto Sans SC. These font licenses are separate from textflowkit's Apache-2.0
+license. Do not remove them from redistributed source or wheels.

textflowkit/render/markdown.py

@@ -0,0 +1,33 @@
+"""Markdown renderer - readable transcript with time anchors."""
+
+from __future__ import annotations
+
+from textflowkit.core.model import Transcript
+from textflowkit.core.timeutil import srt_timestamp
+
+
+def _hms(seconds: float) -> str:
+    return srt_timestamp(seconds).split(",")[0]
+
+
+def render_markdown(transcript: Transcript, *, title: str | None = None) -> str:
+    heading = title or "Transcript"
+    out: list[str] = [f"# {heading}", ""]
+    if transcript.source:
+        out.append(f"**Source:** {transcript.source}")
+    if transcript.language:
+        out.append(f"**Language:** {transcript.language}")
+    if transcript.duration:
+        out.append(f"**Duration:** {_hms(transcript.duration)}")
+    out += ["", "---", ""]
+
+    current_speaker: str | None = None
+    for seg in transcript.segments:
+        if seg.hidden:
+            continue
+        if seg.speaker and seg.speaker != current_speaker:
+            current_speaker = seg.speaker
+            out += [f"**{current_speaker}**", ""]
+        out.append(f"`{_hms(seg.start)}` {seg.display_text().strip()}")
+        out.append("")
+    return "\n".join(out)

textflowkit/render/pdf.py

@@ -0,0 +1,136 @@
+"""PDF renderer.
+
+Binary output, so it does not go through `render()` - see `render_bytes()`.
+
+Like the DOCX renderer this emits the finished data model: speaker labels and
+translated text included.
+"""
+
+from __future__ import annotations
+
+import io
+import threading
+from pathlib import Path
+from xml.sax.saxutils import escape
+
+from textflowkit.core.model import Transcript
+from textflowkit.core.timeutil import srt_timestamp
+
+try:
+    from reportlab.lib.pagesizes import LETTER
+    from reportlab.lib.styles import getSampleStyleSheet
+    from reportlab.lib.units import inch
+    from reportlab.pdfbase import pdfmetrics
+    from reportlab.pdfbase.ttfonts import TTFont
+    from reportlab.platypus import Paragraph, SimpleDocTemplate, Spacer
+except ImportError as exc:  # pragma: no cover - optional extra
+    raise ImportError(
+        "PDF export requires the 'export' extra. Install with: pip install 'textflowkit[export]'"
+    ) from exc
+
+
+def _hms(seconds: float) -> str:
+    return srt_timestamp(seconds).split(",")[0]
+
+
+_FONT_LOCK = threading.Lock()
+_FONT_DIR = Path(__file__).parent / "fonts"
+
+
+def _ensure_fonts() -> None:
+    with _FONT_LOCK:
+        for name in ("NotoSans", "NotoSansArabic", "NotoSansSC"):
+            if name not in pdfmetrics.getRegisteredFontNames():
+                pdfmetrics.registerFont(TTFont(name, str(_FONT_DIR / f"{name}.ttf")))
+            pdfmetrics.registerFontFamily(
+                name, normal=name, bold=name, italic=name, boldItalic=name
+            )
+
+
+def _font_for(char: str) -> str:
+    code = ord(char)
+    if (0x0600 <= code <= 0x06FF or 0x0750 <= code <= 0x077F
+            or 0x08A0 <= code <= 0x08FF or 0xFB50 <= code <= 0xFDFF
+            or 0xFE70 <= code <= 0xFEFF):
+        return "NotoSansArabic"
+    if (0x3000 <= code <= 0x303F or 0x3400 <= code <= 0x9FFF
+            or 0xF900 <= code <= 0xFAFF):
+        return "NotoSansSC"
+    return "NotoSans"
+
+
+def _unicode_markup(text: str) -> str:
+    """Escape text and select embedded fonts for CJK and Arabic runs."""
+    if not text:
+        return ""
+    chunks: list[str] = []
+    current = _font_for(text[0])
+    run: list[str] = []
+    for char in text:
+        font = _font_for(char)
+        if font != current:
+            chunks.append(f'<font name="{current}">{escape("".join(run))}</font>')
+            run = []
+            current = font
+        run.append(char)
+    chunks.append(f'<font name="{current}">{escape("".join(run))}</font>')
+    return "".join(chunks)
+
+
+def render_pdf(transcript: Transcript, *, title: str = "Transcript") -> bytes:
+    """Render a transcript as a PDF."""
+    _ensure_fonts()
+    buffer = io.BytesIO()
+    doc = SimpleDocTemplate(
+        buffer,
+        pagesize=LETTER,
+        title=title,
+        leftMargin=0.9 * inch,
+        rightMargin=0.9 * inch,
+        topMargin=0.9 * inch,
+        bottomMargin=0.9 * inch,
+    )
+    styles = getSampleStyleSheet()
+    for name in ("Title", "Normal", "Heading3", "BodyText"):
+        styles[name].fontName = "NotoSans"
+        styles[name].wordWrap = "LTR"
+        styles[name].shaping = 1
+    story = [Paragraph(_unicode_markup(title), styles["Title"]), Spacer(1, 10)]
+
+    if transcript.source:
+        story.append(Paragraph(f"<b>Source:</b> {_unicode_markup(transcript.source)}", styles["Normal"]))
+    if transcript.language:
+        story.append(Paragraph(f"<b>Language:</b> {_unicode_markup(transcript.language)}", styles["Normal"]))
+    if transcript.duration:
+        story.append(Paragraph(f"<b>Duration:</b> {_hms(transcript.duration)}", styles["Normal"]))
+
+    diar = (transcript.metadata or {}).get("diarization")
+    if diar:
+        speakers = ", ".join(diar.get("speakers") or []) or "none"
+        story.append(Paragraph(f"<b>Speakers:</b> {_unicode_markup(speakers)}", styles["Normal"]))
+    trans = (transcript.metadata or {}).get("translation")
+    if trans:
+        story.append(
+            Paragraph(f"<b>Translated to:</b> {_unicode_markup(str(trans.get('target')))}", styles["Normal"])
+        )
+
+    story.append(Spacer(1, 16))
+
+    current_speaker: str | None = None
+    for segment in transcript.segments:
+        if segment.hidden:
+            continue
+        if segment.speaker and segment.speaker != current_speaker:
+            current_speaker = segment.speaker
+            story.append(Paragraph(f"<b>{_unicode_markup(current_speaker)}</b>", styles["Heading3"]))
+
+        stamp = f"[{_hms(segment.start)}] "
+        if segment.translated_text:
+            body = f"{_unicode_markup(segment.translated_text.strip())}<br/><i>(original: {_unicode_markup(segment.text.strip())})</i>"
+        else:
+            body = _unicode_markup(segment.text.strip())
+        story.append(Paragraph(f"<b>{stamp}</b>{body}", styles["BodyText"]))
+        story.append(Spacer(1, 4))
+
+    doc.build(story)
+    return buffer.getvalue()

textflowkit/render/srt.py

@@ -0,0 +1,22 @@
+"""SRT renderer."""
+
+from __future__ import annotations
+
+from textflowkit.core.model import Transcript
+from textflowkit.core.timeutil import srt_timestamp
+
+
+def render_srt(transcript: Transcript, *, include_translation: bool = True) -> str:
+    blocks: list[str] = []
+    index = 0
+    for seg in transcript.segments:
+        if seg.hidden:
+            continue
+        index += 1
+        body = seg.display_text().strip() if include_translation else seg.text.strip()
+        if seg.speaker:
+            body = f"{seg.speaker}: {body}"
+        blocks.append(
+            f"{index}\n{srt_timestamp(seg.start)} --> {srt_timestamp(seg.end)}\n{body}\n"
+        )
+    return "\n".join(blocks)

textflowkit/render/txt.py

@@ -0,0 +1,19 @@
+"""Plain-text renderer."""
+
+from __future__ import annotations
+
+from textflowkit.core.model import Transcript
+
+
+def render_txt(transcript: Transcript, *, timestamps: bool = False, speaker: bool = False) -> str:
+    lines: list[str] = []
+    for seg in transcript.segments:
+        if seg.hidden:
+            continue
+        prefix = ""
+        if timestamps:
+            prefix = f"[{seg.start:8.2f}] "
+        if speaker and seg.speaker:
+            prefix += f"{seg.speaker}: "
+        lines.append(prefix + seg.display_text().strip())
+    return "\n".join(lines) + ("\n" if lines else "")

textflowkit/render/vtt.py

@@ -0,0 +1,20 @@
+"""WebVTT renderer."""
+
+from __future__ import annotations
+
+from textflowkit.core.model import Transcript
+from textflowkit.core.timeutil import vtt_timestamp
+
+
+def render_vtt(transcript: Transcript, *, include_translation: bool = True) -> str:
+    lines: list[str] = ["WEBVTT", ""]
+    for seg in transcript.segments:
+        if seg.hidden:
+            continue
+        body = seg.display_text().strip() if include_translation else seg.text.strip()
+        if seg.speaker:
+            body = f"<v {seg.speaker}>{body}"
+        lines.append(f"{vtt_timestamp(seg.start)} --> {vtt_timestamp(seg.end)}")
+        lines.append(body)
+        lines.append("")
+    return "\n".join(lines)

textflowkit/sources/__init__.py

@@ -0,0 +1,16 @@
+"""Source layer: platform detection and media acquisition."""
+
+from textflowkit.sources.acquire import AcquisitionError, extract_audio, fetch_media, require_tool
+from textflowkit.sources.detect import PLATFORMS, SourceRef, detect_platform, is_url, resolve_source
+
+__all__ = [
+    "PLATFORMS",
+    "AcquisitionError",
+    "SourceRef",
+    "detect_platform",
+    "extract_audio",
+    "fetch_media",
+    "is_url",
+    "require_tool",
+    "resolve_source",
+]