//! Structure-tree and accessibility acceptance tests.
//!
//! The merge criteria from `REVIEWS/adr/0011-pdf-structure-tree.md`.
//!
//! The most valuable test here is not about accessibility at all:
//! [`bmc_no_longer_turns_red_into_green`] guards a colour-corruption bug
//! that affected every tagged document.

use std::path::PathBuf;

use nigig_pdf_document::structure::{AccessibilityIssue, StructRole};
use nigig_pdf_document::PdfDocument;
use nigig_pdf_graphics::content::parse_content_stream;
use nigig_pdf_graphics::recording::{RecordingDevice, RenderCommand};

fn corpus(relative: &str) -> Vec<u8> {
    let path = PathBuf::from(env!("CARGO_MANIFEST_DIR"))
        .join("../tests/corpus")
        .join(relative);
    std::fs::read(&path).unwrap_or_else(|e| panic!("missing {}: {e}", path.display()))
}

/// `BMC` never matched its dispatch arm, so it was neither recognised nor
/// *cleared from the operand stack*. The leftover `/Tag` shifted the
/// operands of every following operator: `1 0 0 rg` became
/// `RgbFill(0.0, 1.0, 0.0)`.
///
/// Tagged documents are exactly the ones containing `BMC`, so the documents
/// that tried hardest to be accessible rendered with the wrong colours.
#[test]
fn bmc_no_longer_turns_red_into_green() {
    let bytes = corpus("structure/marked_content_colour.pdf");
    let mut doc = PdfDocument::parse(&bytes).expect("parses");
    let page = doc.page(0).expect("page 0");
    let ops = parse_content_stream(&page.content_data).expect("content parses");
    let cmds = RecordingDevice::from_ops(&ops);

    let fill = cmds
        .iter()
        .find_map(|c| match c {
            RenderCommand::SetFillColor(c) => Some(*c),
            _ => None,
        })
        .expect("the page fills a rectangle");

    assert!(
        (fill[0] - 1.0).abs() < 1e-9 && fill[1].abs() < 1e-9 && fill[2].abs() < 1e-9,
        "the page fills red, but got {fill:?} - BMC shifted the operands"
    );
}

#[test]
fn a_tagged_document_yields_its_tree() {
    let bytes = corpus("structure/tagged.pdf");
    let mut doc = PdfDocument::parse(&bytes).expect("parses");
    let tree = doc.structure_tree().expect("structure tree");

    assert!(!tree.untagged);
    assert!(tree.marked, "/MarkInfo /Marked true");
    assert_eq!(tree.lang.as_deref(), Some("en-GB"));
    assert_eq!(tree.elements.len(), 4);

    let order = tree.reading_order();
    let roles: Vec<&StructRole> = order.iter().map(|i| &tree.elements[*i].role).collect();
    assert_eq!(
        roles,
        vec![
            &StructRole::Document,
            &StructRole::Heading(Some(1)),
            &StructRole::Paragraph,
            &StructRole::Figure,
        ]
    );
}

#[test]
fn reading_order_is_depth_first_not_geometric() {
    let bytes = corpus("structure/tagged.pdf");
    let mut doc = PdfDocument::parse(&bytes).expect("parses");
    let tree = doc.structure_tree().expect("tree");

    let order = tree.reading_order();
    // The Document root must precede all of its children.
    assert_eq!(tree.elements[order[0]].role, StructRole::Document);
    for i in &order[1..] {
        assert_eq!(
            tree.elements[*i].parent,
            Some(order[0]),
            "every other element is a child of the root here"
        );
    }
}

#[test]
fn mcids_link_content_to_its_structure_element() {
    let bytes = corpus("structure/tagged.pdf");
    let mut doc = PdfDocument::parse(&bytes).expect("parses");
    let tree = doc.structure_tree().expect("tree");

    // The heading owns MCID 0, the paragraph 1, the figure 2.
    for (mcid, expected) in [
        (0, StructRole::Heading(Some(1))),
        (1, StructRole::Paragraph),
        (2, StructRole::Figure),
    ] {
        let el = tree
            .element_for_mcid(None, mcid)
            .unwrap_or_else(|| panic!("no element owns MCID {mcid}"));
        assert_eq!(el.role, expected, "MCID {mcid}");
    }
}

/// The `/MCID` must survive all the way to the device, or the tree cannot
/// be attached to what was actually drawn.
#[test]
fn mcids_reach_the_device() {
    let bytes = corpus("structure/tagged.pdf");
    let mut doc = PdfDocument::parse(&bytes).expect("parses");
    let page = doc.page(0).expect("page 0");
    let ops = parse_content_stream(&page.content_data).expect("parses");
    let cmds = RecordingDevice::from_ops(&ops);

    let mcids: Vec<i64> = cmds
        .iter()
        .filter_map(|c| match c {
            RenderCommand::BeginMarkedContent { mcid, .. } => *mcid,
            _ => None,
        })
        .collect();
    assert_eq!(
        mcids,
        vec![0, 1, 2],
        "every BDC's /MCID must reach the device"
    );
}

#[test]
fn alt_text_is_exposed() {
    let bytes = corpus("structure/tagged.pdf");
    let mut doc = PdfDocument::parse(&bytes).expect("parses");
    let tree = doc.structure_tree().expect("tree");

    let figure = tree
        .elements
        .iter()
        .find(|e| e.role == StructRole::Figure)
        .expect("a figure");
    assert_eq!(
        figure.alt.as_deref(),
        Some("A red rectangle illustrating the layout")
    );
    assert_eq!(figure.description(), figure.alt.as_deref());
}

#[test]
fn a_role_map_translates_custom_tags() {
    let bytes = corpus("structure/role_map.pdf");
    let mut doc = PdfDocument::parse(&bytes).expect("parses");
    let tree = doc.structure_tree().expect("tree");

    assert_eq!(tree.role_map.get("Chapter").map(String::as_str), Some("H1"));

    let chapter = tree
        .elements
        .iter()
        .find(|e| e.raw_type == "Chapter")
        .expect("the custom-tagged element");
    assert_eq!(
        chapter.role,
        StructRole::Heading(Some(1)),
        "/RoleMap must map /Chapter onto /H1"
    );
    // The original tag is kept, so a caller can see it was remapped.
    assert_eq!(chapter.raw_type, "Chapter");

    let body = tree
        .elements
        .iter()
        .find(|e| e.raw_type == "BodyCopy")
        .expect("the second custom tag");
    assert_eq!(body.role, StructRole::Paragraph);
}

#[test]
fn accessibility_faults_are_each_reported() {
    let bytes = corpus("structure/inaccessible.pdf");
    let mut doc = PdfDocument::parse(&bytes).expect("parses");
    let tree = doc.structure_tree().expect("tree");
    let findings = tree.findings();

    assert!(
        findings.contains(&AccessibilityIssue::NoDocumentLanguage),
        "{:?}",
        findings.issues
    );
    assert!(
        findings
            .issues
            .iter()
            .any(|i| matches!(i, AccessibilityIssue::FigureWithoutAlt { .. })),
        "{:?}",
        findings.issues
    );
    assert!(
        findings.issues.iter().any(|i| matches!(
            i,
            AccessibilityIssue::HeadingLevelSkipped { from: 1, to: 3, .. }
        )),
        "{:?}",
        findings.issues
    );
}

#[test]
fn a_well_formed_document_reports_no_issues() {
    let bytes = corpus("structure/tagged.pdf");
    let mut doc = PdfDocument::parse(&bytes).expect("parses");
    let tree = doc.structure_tree().expect("tree");
    let findings = tree.findings();
    assert!(
        findings.no_issues_found(),
        "unexpected findings: {:?}",
        findings.issues
    );
}

#[test]
fn a_cell_outside_a_row_is_reported_on_a_real_document() {
    let bytes = corpus("structure/table.pdf");
    let mut doc = PdfDocument::parse(&bytes).expect("parses");
    let tree = doc.structure_tree().expect("tree");
    let findings = tree.findings();
    assert!(
        findings
            .issues
            .iter()
            .any(|i| matches!(i, AccessibilityIssue::CellOutsideRow { .. })),
        "the un-rowed cell was not reported: {:?}",
        findings.issues
    );
}

/// A `/K` graph pointing back at an ancestor must be cut, not expanded
/// until the depth bound, and certainly not recursed until the stack dies.
#[test]
fn a_cyclic_structure_tree_terminates_and_is_reported() {
    let bytes = corpus("structure/cyclic.pdf");
    let mut doc = PdfDocument::parse(&bytes).expect("parses");
    let tree = doc.structure_tree().expect("a cyclic tree must not error");

    assert_eq!(
        tree.elements.len(),
        2,
        "the cycle must be cut at first repeat, not expanded: {:?}",
        tree.elements.len()
    );
    assert!(
        !tree.cycles_cut.is_empty(),
        "the cycle must be reported, not silently pruned"
    );
    assert!(tree
        .findings()
        .issues
        .iter()
        .any(|i| matches!(i, AccessibilityIssue::CyclicStructure { .. })));
}

/// An untagged document must report as untagged, which is a different state
/// from a tagged document whose tree happens to be empty.
#[test]
fn an_untagged_document_says_so() {
    let bytes = corpus("structure/untagged.pdf");
    let mut doc = PdfDocument::parse(&bytes).expect("parses");
    let tree = doc.structure_tree().expect("tree");

    assert!(tree.untagged);
    assert!(tree.elements.is_empty());
    assert_eq!(
        tree.findings().issues,
        vec![AccessibilityIssue::NotTagged],
        "an untagged document has one finding, not a pile of derived ones"
    );
}

/// ADR 0011 rule 4: mechanical checks are not a conformance verdict.
///
/// This asserts the *absence* of a conformance API. If someone adds an
/// `is_pdf_ua` or similar, this test is where the argument happens.
#[test]
fn nothing_claims_pdf_ua_conformance() {
    let bytes = corpus("structure/tagged.pdf");
    let mut doc = PdfDocument::parse(&bytes).expect("parses");
    let tree = doc.structure_tree().expect("tree");
    let findings = tree.findings();

    // The only verdict offered is "these particular checks found nothing".
    assert!(findings.no_issues_found());

    // Tripwire for a future rename. Comment lines are skipped so that the
    // module documentation can go on explaining *why* there is no
    // conformance verdict without tripping the check that enforces it.
    let source = include_str!("../src/structure.rs");
    let code_only: String = source
        .lines()
        .filter(|l| {
            let t = l.trim_start();
            !t.starts_with("//") && !t.starts_with("*")
        })
        .collect::<Vec<_>>()
        .join("\n");
    for forbidden in ["is_pdf_ua", "is_conformant", "ComplianceReport"] {
        assert!(
            !code_only.contains(forbidden),
            "structure.rs gained `{forbidden}` in code; mechanical checks \
             cannot decide PDF/UA conformance (ADR 0011 rule 4)"
        );
    }
}

#[test]
fn every_structure_fixture_parses_without_panicking() {
    for name in [
        "tagged.pdf",
        "role_map.pdf",
        "inaccessible.pdf",
        "cyclic.pdf",
        "untagged.pdf",
        "table.pdf",
        "marked_content_colour.pdf",
    ] {
        let bytes = corpus(&format!("structure/{name}"));
        let mut doc = PdfDocument::parse(&bytes)
            .unwrap_or_else(|e| panic!("structure/{name} should parse: {e}"));
        let tree = doc.structure_tree();
        if let Ok(t) = tree {
            let _ = t.findings();
            let _ = t.reading_order();
            let _ = t.headings();
        }
        let _ = doc.page(0);
    }
}