mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-10-25 02:29:31 -06:00
snipeTRandBrandon Thomas
9035ae3c82
Text files were decoded with String::from_utf8_lossy wherever they are
read: Create PDF and Combine from a .txt file, the automation `create`
tool's text `path`, and Search & Redact's word list file. So
- a UTF-16 file (Windows Notepad's "Unicode") became NULs and replacement
characters ("??G?r?????e?" for "Grüße"),
- a UTF-8 byte order mark became a stray character at the start, and
- a Windows-1252 or 1254 file lost every accented letter ("caf�", "K��").
For a word list that means the words were never found and stayed
unredacted.
pdfcraft_create::decode_text picks UTF-8 or UTF-16 (LE/BE) by the byte
order mark and drops it, keeps valid UTF-8, and otherwise decodes the
Windows code page: 1254 when the bytes 1254 uses for Ğ İ Ş ğ ı ş appear
without á í ó ú (which Turkish never writes but Icelandic and Faroese,
the only Western languages using those bytes, always do), else 1252.
encoding_rs is already in the build through lopdf.
Co-authored-by: Brandon Thomas <echelon@gmail.com>
25 lines
758 B
TOML
25 lines
758 B
TOML
[package]
|
|
name = "pdfcraft-create"
|
|
description = "Create PDFs: blank documents, from images (PNG, JPEG) and from plain text"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
license.workspace = true
|
|
|
|
[lints]
|
|
workspace = true
|
|
|
|
[dependencies]
|
|
pdfcraft-cos = { workspace = true }
|
|
pdfcraft-model = { workspace = true }
|
|
pdfcraft-fonts = { workspace = true }
|
|
png = "0.18"
|
|
tiff = "0.11"
|
|
image = { version = "0.25", default-features = false, features = ["bmp", "gif", "jpeg"] }
|
|
thiserror = { workspace = true }
|
|
# Already in the graph through lopdf; used only to read plain-text files (decode_text).
|
|
encoding_rs = "0.8"
|
|
|
|
[dev-dependencies]
|
|
image = { version = "0.25", default-features = false, features = ["bmp", "gif", "jpeg"] }
|
|
hayro-syntax = { workspace = true }
|