tiny.pdf.extractTextAlloc

1pub fn extractTextAlloc(2    text_allocator: std.mem.Allocator,3    filter_storage: *filter.Storage,4    bytes: []const u8,5) ![]u8 {6    var document = try Document.init(text_allocator, filter_storage, bytes);7    defer document.deinit();8    var pages: std.ArrayList(Page) = .empty;9    defer pages.deinit(text_allocator);10    try document.pagesAppend(text_allocator, &pages);11    var out = std.ArrayList(u8).empty;12    errdefer out.deinit(text_allocator);13    for (pages.items) |page| {14        const fonts = try document.fontSetAlloc(page.resources);15        for (page.contents) |reference| {16            const stream = try document.objectStream(reference);17            {18                const decoded = try document.decodeStream(stream);19                defer filter_storage.reset();20                try content.extractTextAppend(text_allocator, &out, decoded, fonts);21            }22        }23    }24    return try out.toOwnedSlice(text_allocator);25}

1pub const extractTextAlloc = @import("document.zig").extractTextAlloc;