imprimatur 0.2.0 → 0.4.0

data/lib/imprimatur.rb

@@ -6,9 +6,11 @@ require_relative 'imprimatur/formula'
 require_relative 'imprimatur/native'
 require_relative 'imprimatur/style'
 require_relative 'imprimatur/validation'
+require_relative 'imprimatur/barcode'
 require_relative 'imprimatur/xlsx'
 require_relative 'imprimatur/document'
 require_relative 'imprimatur/reader'
+require_relative 'imprimatur/spreadsheet'
 require_relative 'imprimatur/zip'
 
 # Document authoring with a native core: XLSX workbooks, and PDF and DOCX from
@@ -25,7 +27,7 @@ require_relative 'imprimatur/zip'
 module Imprimatur
   class << self
     # @see Xlsx.build
-    def xlsx(path = nil, &) = Xlsx.build(path, &)
+    def xlsx(path = nil, **, &) = Xlsx.build(path, **, &)
 
     # @param expression [String] such as +"SUM(A1:A3)"+ or +"=A1*2"+
     # @return [Formula]
@@ -37,6 +39,9 @@ module Imprimatur
     # @see Validation.build
     def validation(**) = Validation.build(**)
 
+    # @see Barcode.encode
+    def barcode(symbology, data, **) = Barcode.encode(symbology, data, **)
+
     # Builds a {Document} and renders it as PDF. With a path, saves it there
     # and returns the path; without, returns the bytes.
     #
@@ -78,18 +83,29 @@ module Imprimatur
     # (+heading+, +paragraph+) with their +:bounds+ in points from the
     # page's top-left corner; a workbook's +:sheets+ of +:rows+ of typed
     # +:cells+ (+number+, +date+, +bool+, +text+, +error+, +formula+) and
-    # +:comments+; a Word document's +:blocks+ (+heading+, +paragraph+,
+    # +:comments+, and from an +.xlsx+ its +:columns+ widths and data
+    # +:validations+; a Word document's +:blocks+ (+heading+, +paragraph+,
     # +list_item+, +table+), their bold, italic and linked +:marks+ as byte
     # ranges. Dates are ISO 8601 strings: Excel's have no time zone.
     #
     #   sheet = Imprimatur.content('sales.xlsx')[:sheets].first
     #   sheet[:rows][1][:cells]  # => [{cell: "A2", type: "text", value: "North"}, ...]
     #
-    # Takes the arguments of {.markdown}, and raises as it does.
+    # Takes the arguments of {.markdown}, and raises as it does. With
+    # +styles: true+ each sheet also lists its formatted cells' +:styles+:
+    # font, size, bold, italic, underline, ARGB color and fill, alignment,
+    # wrap, border and number format.
     #
     # @return [Hash] with symbol keys; +:format+ is +"pdf"+, +"xlsx"+ or +"docx"+
     def content(document, ...) = Reader.content(document, ...)
 
+    # A workbook's sheets and their values, read from the same documents
+    # {.markdown} takes (+.xlsx+, +.xls+, +.ods+); see {Spreadsheet}.
+    #
+    # @return [Spreadsheet]
+    # @raise [UnsupportedDocument] a PDF, a Word document or another format
+    def spreadsheet(document, ...) = Spreadsheet.open(document, ...)
+
     # A document's images, as files: a PDF's, once each, from the first page
     # that draws them (JPEG and JPEG 2000 as stored, fax scans as TIFF, raw
     # pixels as PNG); a Word or Excel document's media. A scanned PDF gives

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: imprimatur
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.4.0
 platform: ruby
 authors:
 - Abdelkader Boudih
@@ -52,11 +52,21 @@ files:
 - ext/imprimatur_native/core/LICENSE
 - ext/imprimatur_native/core/README.md
 - ext/imprimatur_native/core/src/archive.rs
+- ext/imprimatur_native/core/src/barcode.rs
+- ext/imprimatur_native/core/src/barcode/code128.rs
+- ext/imprimatur_native/core/src/barcode/draw.rs
+- ext/imprimatur_native/core/src/barcode/ean.rs
+- ext/imprimatur_native/core/src/barcode/gs1.rs
+- ext/imprimatur_native/core/src/barcode/matrix.rs
 - ext/imprimatur_native/core/src/doc.rs
 - ext/imprimatur_native/core/src/doc/paragraph.rs
+- ext/imprimatur_native/core/src/doc/picture.rs
+- ext/imprimatur_native/core/src/doc/symbol.rs
 - ext/imprimatur_native/core/src/doc/table.rs
 - ext/imprimatur_native/core/src/docx.rs
+- ext/imprimatur_native/core/src/docx/picture.rs
 - ext/imprimatur_native/core/src/error.rs
+- ext/imprimatur_native/core/src/font.rs
 - ext/imprimatur_native/core/src/lib.rs
 - ext/imprimatur_native/core/src/opc.rs
 - ext/imprimatur_native/core/src/pdf.rs
@@ -65,6 +75,10 @@ files:
 - ext/imprimatur_native/core/src/pdf/layout/wrap.rs
 - ext/imprimatur_native/core/src/pdf/metrics.rs
 - ext/imprimatur_native/core/src/pdf/objects.rs
+- ext/imprimatur_native/core/src/pdf/picture.rs
+- ext/imprimatur_native/core/src/pdf/truetype.rs
+- ext/imprimatur_native/core/src/pdf/truetype/descriptor.rs
+- ext/imprimatur_native/core/src/pdf/truetype/program.rs
 - ext/imprimatur_native/core/src/read.rs
 - ext/imprimatur_native/core/src/read/budget.rs
 - ext/imprimatur_native/core/src/read/content.rs
@@ -92,6 +106,7 @@ files:
 - ext/imprimatur_native/core/src/read/pdf/glyphs.txt
 - ext/imprimatur_native/core/src/read/pdf/images.rs
 - ext/imprimatur_native/core/src/read/pdf/layout.rs
+- ext/imprimatur_native/core/src/read/pdf/layout/bidi.rs
 - ext/imprimatur_native/core/src/read/pdf/lexer.rs
 - ext/imprimatur_native/core/src/read/pdf/object.rs
 - ext/imprimatur_native/core/src/read/pdf/object/name.rs
@@ -100,9 +115,11 @@ files:
 - ext/imprimatur_native/core/src/read/xls.rs
 - ext/imprimatur_native/core/src/read/xls/strings.rs
 - ext/imprimatur_native/core/src/read/xlsx.rs
+- ext/imprimatur_native/core/src/read/xlsx/formats.rs
+- ext/imprimatur_native/core/src/script.rs
 - ext/imprimatur_native/core/src/style.rs
-- ext/imprimatur_native/core/src/test_support.rs
 - ext/imprimatur_native/core/src/xlsx.rs
+- ext/imprimatur_native/core/src/xlsx/autofit.rs
 - ext/imprimatur_native/core/src/xlsx/cell.rs
 - ext/imprimatur_native/core/src/xlsx/comment.rs
 - ext/imprimatur_native/core/src/xlsx/date.rs
@@ -120,19 +137,23 @@ files:
 - ext/imprimatur_native/extconf.rb
 - ext/imprimatur_native/ffi/Cargo.toml
 - ext/imprimatur_native/ffi/src/archive.rs
+- ext/imprimatur_native/ffi/src/barcode.rs
 - ext/imprimatur_native/ffi/src/blocking.rs
 - ext/imprimatur_native/ffi/src/convert.rs
 - ext/imprimatur_native/ffi/src/document.rs
 - ext/imprimatur_native/ffi/src/lib.rs
 - ext/imprimatur_native/ffi/src/read.rs
+- ext/imprimatur_native/ffi/src/sheets.rs
 - ext/imprimatur_native/ffi/src/style.rs
 - ext/imprimatur_native/ffi/src/validation.rs
 - lib/imprimatur.rb
+- lib/imprimatur/barcode.rb
 - lib/imprimatur/document.rb
 - lib/imprimatur/error.rb
 - lib/imprimatur/formula.rb
 - lib/imprimatur/native.rb
 - lib/imprimatur/reader.rb
+- lib/imprimatur/spreadsheet.rb
 - lib/imprimatur/style.rb
 - lib/imprimatur/validation.rb
 - lib/imprimatur/version.rb

data/ext/imprimatur_native/core/src/test_support.rs

@@ -1,250 +0,0 @@
-//! Helpers shared by the unit tests.
-
-use std::io::{Cursor, Read};
-
-/// Every entry of a zip archive as `(name, bytes)`, read with the `zip`
-/// crate: an implementation independent of ours, which verifies each CRC.
-pub fn read_zip(bytes: Vec<u8>) -> Vec<(String, Vec<u8>)> {
-    let mut archive = ::zip::ZipArchive::new(Cursor::new(bytes)).unwrap();
-    (0..archive.len())
-        .map(|index| {
-            let mut file = archive.by_index(index).unwrap();
-            let mut data = Vec::new();
-            file.read_to_end(&mut data).unwrap();
-            (file.name().unwrap().into_owned(), data)
-        })
-        .collect()
-}
-
-/// Every entry of a zip archive as text, by name, read as [`read_zip`] does.
-pub fn text_parts(bytes: Vec<u8>) -> Vec<(String, String)> {
-    read_zip(bytes)
-        .into_iter()
-        .map(|(name, data)| (name, String::from_utf8(data).unwrap()))
-        .collect()
-}
-
-/// The text of the part `name` among `parts`.
-pub fn part<'a>(parts: &'a [(String, String)], name: &str) -> &'a str {
-    parts
-        .iter()
-        .find(|(part, _)| part == name)
-        .map_or_else(|| panic!("no part {name}"), |(_, xml)| xml)
-}
-
-/// A zip of `(name, text)` parts, written with our own writer.
-pub fn zip_of(parts: &[(&str, &str)]) -> Vec<u8> {
-    let mut zip = crate::zip::ZipWriter::new(Vec::new());
-    for (name, text) in parts {
-        zip.add(name, text.as_bytes()).unwrap();
-    }
-    zip.finish().unwrap()
-}
-
-/// A PDF of `objects`, numbered from 1 (the first is the catalog), with a
-/// classic cross-reference table.
-pub fn pdf_of(objects: &[Vec<u8>]) -> Vec<u8> {
-    use std::io::Write as _;
-    let mut out = b"%PDF-1.7\n%\xE2\xE3\xCF\xD3\n".to_vec();
-    let mut offsets = Vec::new();
-    for (number, body) in (1..).zip(objects) {
-        offsets.push(out.len());
-        writeln!(out, "{number} 0 obj").unwrap();
-        out.extend_from_slice(body);
-        out.extend_from_slice(b"\nendobj\n");
-    }
-    let xref = out.len();
-    write!(out, "xref\n0 {}\n0000000000 65535 f \n", objects.len() + 1).unwrap();
-    for offset in offsets {
-        writeln!(out, "{offset:010} 00000 n ").unwrap();
-    }
-    write!(
-        out,
-        "trailer\n<< /Size {} /Root 1 0 R >>\nstartxref\n{xref}\n%%EOF\n",
-        objects.len() + 1
-    )
-    .unwrap();
-    out
-}
-
-/// A stream object: `dict` holds the entries besides `/Length`.
-pub fn stream_object(dict: &str, data: &[u8]) -> Vec<u8> {
-    let mut out = format!("<< /Length {} {dict} >>\nstream\n", data.len()).into_bytes();
-    out.extend_from_slice(data);
-    out.extend_from_slice(b"\nendstream");
-    out
-}
-
-/// One page of `content` with Helvetica as `/F1` and a 612 by 792 page.
-pub fn page_pdf(content: &str, page_extra: &str) -> Vec<u8> {
-    pdf_of(&[
-        b"<< /Type /Catalog /Pages 2 0 R >>".to_vec(),
-        b"<< /Type /Pages /Kids [3 0 R] /Count 1 >>".to_vec(),
-        format!(
-            "<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] \
-             /Resources << /Font << /F1 4 0 R >> >> /Contents 5 0 R {page_extra} >>"
-        )
-        .into_bytes(),
-        b"<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica /Encoding /WinAnsiEncoding >>"
-            .to_vec(),
-        stream_object("", content.as_bytes()),
-    ])
-}
-
-/// A PNG as `read::image::png` writes it, read back.
-#[derive(Debug)]
-pub struct Png {
-    pub width: u32,
-    pub height: u32,
-    pub bits: u8,
-    pub color: u8,
-    pub palette: Option<Vec<u8>>,
-    /// The rows, their filter bytes (always 0, none) taken out.
-    pub rows: Vec<u8>,
-}
-
-/// Reads a PNG, checking each chunk's CRC and that every row is unfiltered.
-pub fn png_of(data: &[u8]) -> Png {
-    let be = |at: usize| u32::from_be_bytes(data[at..at + 4].try_into().unwrap());
-    assert!(data.starts_with(b"\x89PNG\r\n\x1a\n"), "{data:?}");
-    let (mut header, mut palette, mut compressed) = (Vec::new(), None, Vec::new());
-    let mut at = 8;
-    while at < data.len() {
-        let length = be(at) as usize;
-        let (kind, body) = (&data[at + 4..at + 8], &data[at + 8..at + 8 + length]);
-        assert_eq!(
-            be(at + 8 + length),
-            crc32fast::hash(&data[at + 4..at + 8 + length]),
-            "{kind:?}"
-        );
-        match kind {
-            b"IHDR" => header = body.to_vec(),
-            b"PLTE" => palette = Some(body.to_vec()),
-            b"IDAT" => compressed.extend_from_slice(body),
-            _ => {}
-        }
-        at += 12 + length;
-    }
-    let (width, height) = (be(16), be(20));
-    let (bits, color) = (header[8], header[9]);
-    let channels = match color {
-        0 | 3 => 1,
-        4 => 2,
-        2 => 3,
-        _ => 4,
-    };
-    let stride = (width as usize * channels * usize::from(bits)).div_ceil(8);
-    let filtered = miniz_oxide::inflate::decompress_to_vec_zlib(&compressed).unwrap();
-    assert_eq!(filtered.len(), (stride + 1) * height as usize);
-    let mut rows = Vec::new();
-    for row in filtered.chunks(stride + 1) {
-        assert_eq!(row[0], 0, "filter type");
-        rows.extend_from_slice(&row[1..]);
-    }
-    Png { width, height, bits, color, palette, rows }
-}
-
-/// A one-strip little-endian TIFF's tags, by number, and its strip.
-pub fn tiff_of(data: &[u8]) -> (std::collections::BTreeMap<u16, u32>, &[u8]) {
-    let le16 = |at: usize| u16::from_le_bytes(data[at..at + 2].try_into().unwrap());
-    let le32 = |at: usize| u32::from_le_bytes(data[at..at + 4].try_into().unwrap());
-    assert!(data.starts_with(b"II*\0"));
-    let directory = le32(4) as usize;
-    let tags: std::collections::BTreeMap<u16, u32> = (0..usize::from(le16(directory)))
-        .map(|index| {
-            let entry = directory + 2 + index * 12;
-            let value =
-                if le16(entry + 2) == 3 { u32::from(le16(entry + 8)) } else { le32(entry + 8) };
-            (le16(entry), value)
-        })
-        .collect();
-    let (offset, length) = (tags[&273] as usize, tags[&279] as usize);
-    (tags, &data[offset..offset + length])
-}
-
-/// A compound file (MS-CFB, version 3) holding one stream named `name` in
-/// its root storage; a stream under 4096 bytes goes to the mini stream, as
-/// writers put it.
-pub fn ole_of(name: &str, stream: &[u8]) -> Vec<u8> {
-    const SECTOR: usize = 512;
-    const END: u32 = 0xFFFF_FFFE;
-    let small = stream.len() < 4096;
-    let pad = |data: &[u8], size: usize| {
-        let mut data = data.to_vec();
-        data.resize(data.len().div_ceil(size).max(1) * size, 0);
-        data
-    };
-    // Sectors: FAT, directory, mini FAT (when small), then the data: the
-    // stream itself, or the mini stream holding it.
-    let data = if small { pad(stream, 64) } else { stream.to_vec() };
-    let data_sectors = data.len().div_ceil(SECTOR).max(1);
-    let first_data = if small { 3 } else { 2 };
-    let mut fat = vec![0xFFFF_FFFD_u32, END];
-    if small {
-        fat.push(END);
-    }
-    fat.extend((0..data_sectors).map(|index| {
-        if index + 1 == data_sectors { END } else { u32::try_from(first_data + index + 1).unwrap() }
-    }));
-    fat.resize(SECTOR / 4, 0xFFFF_FFFF);
-    let mut header = vec![0_u8; SECTOR];
-    header[..8].copy_from_slice(&[0xD0, 0xCF, 0x11, 0xE0, 0xA1, 0xB1, 0x1A, 0xE1]);
-    let put = |bytes: &mut Vec<u8>, at: usize, value: u32| {
-        bytes[at..at + 4].copy_from_slice(&value.to_le_bytes());
-    };
-    header[0x18..0x1A].copy_from_slice(&0x3E_u16.to_le_bytes());
-    header[0x1A..0x1C].copy_from_slice(&3_u16.to_le_bytes());
-    header[0x1C..0x1E].copy_from_slice(&0xFFFE_u16.to_le_bytes());
-    header[0x1E..0x20].copy_from_slice(&9_u16.to_le_bytes());
-    header[0x20..0x22].copy_from_slice(&6_u16.to_le_bytes());
-    put(&mut header, 0x2C, 1);
-    put(&mut header, 0x30, 1);
-    put(&mut header, 0x38, 4096);
-    put(&mut header, 0x3C, if small { 2 } else { END });
-    put(&mut header, 0x40, u32::from(small));
-    put(&mut header, 0x44, END);
-    put(&mut header, 0x4C, 0);
-    for index in 1..109 {
-        put(&mut header, 0x4C + index * 4, 0xFFFF_FFFF);
-    }
-    let entry = |name: &str, kind: u8, child: u32, start: u32, size: usize| {
-        let mut bytes = vec![0_u8; 128];
-        let units: Vec<u16> = name.encode_utf16().collect();
-        for (index, unit) in units.iter().enumerate() {
-            bytes[index * 2..index * 2 + 2].copy_from_slice(&unit.to_le_bytes());
-        }
-        bytes[0x40..0x42]
-            .copy_from_slice(&u16::try_from(units.len() * 2 + 2).unwrap().to_le_bytes());
-        bytes[0x42] = kind;
-        for at in [0x44, 0x48, 0x4C] {
-            put(&mut bytes, at, 0xFFFF_FFFF);
-        }
-        put(&mut bytes, 0x4C, child);
-        put(&mut bytes, 0x74, start);
-        put(&mut bytes, 0x78, u32::try_from(size).unwrap());
-        bytes
-    };
-    let first = u32::try_from(first_data).unwrap();
-    let mut directory = if small {
-        let mut directory = entry("Root Entry", 5, 1, first, data.len());
-        directory.extend(entry(name, 2, 0xFFFF_FFFF, 0, stream.len()));
-        directory
-    } else {
-        let mut directory = entry("Root Entry", 5, 1, END, 0);
-        directory.extend(entry(name, 2, 0xFFFF_FFFF, first, stream.len()));
-        directory
-    };
-    directory.resize(SECTOR, 0);
-    let mut file = header;
-    file.extend(fat.iter().flat_map(|word| word.to_le_bytes()));
-    file.extend(directory);
-    if small {
-        let mut mini_fat: Vec<u32> =
-            (1..data.len() / 64).map(|next| u32::try_from(next).unwrap()).collect();
-        mini_fat.push(END);
-        mini_fat.resize(SECTOR / 4, 0xFFFF_FFFF);
-        file.extend(mini_fat.iter().flat_map(|word| word.to_le_bytes()));
-    }
-    file.extend(pad(&data, SECTOR));
-    file
-}