Merge branch 'dev' of https://gitea.maskantech.in/gitea_admin/pdf into furqan

engine/include/pdfengine/ast.hpp

@@ -0,0 +1,44 @@
+#pragma once
+
+#include <string>
+#include <vector>
+#include <unordered_map>
+#include <cstdint>
+#include <memory>
+
+namespace pdfengine {
+
+enum class AstNodeType {
+    Number,
+    Name,
+    String,
+    HexString,
+    Boolean,
+    Null,
+    Array,
+    Dictionary
+};
+
+class AstNode {
+public:
+    AstNodeType type;
+    std::string stringValue;
+    std::vector<uint8_t> bytesValue;
+    double numberValue = 0.0;
+    bool boolValue = false;
+    
+    // We use a vector of shared_ptr for recursive data structures so the node is easily copyable/movable
+    std::vector<std::shared_ptr<AstNode>> arrayItems;
+    std::unordered_map<std::string, std::shared_ptr<AstNode>> dictItems;
+
+    // Constructors for convenience
+    AstNode() = default;
+    explicit AstNode(AstNodeType t) : type(t) {}
+};
+
+struct Operation {
+    std::string op;
+    std::vector<std::shared_ptr<AstNode>> operands;
+};
+
+} // namespace pdfengine

engine/include/pdfengine/content_object.hpp

@@ -0,0 +1,35 @@
+#pragma once
+
+#include <string>
+#include <vector>
+#include <memory>
+
+namespace pdfengine {
+
+enum class ContentObjectType {
+    Text,
+    Path,
+    Image,
+    Unknown
+};
+
+class ContentObject {
+public:
+    virtual ~ContentObject() = default;
+    virtual ContentObjectType getType() const = 0;
+};
+
+class TextObject : public ContentObject {
+public:
+    ContentObjectType getType() const override { return ContentObjectType::Text; }
+    
+    std::string text;           // The decoded text string
+    std::string fontName;       // Font resource name (e.g. "F1")
+    double fontSize = 0.0;      // Font size
+    
+    // Text Transformation Matrix (a, b, c, d, e, f)
+    // Default is identity matrix: [1 0 0 1 0 0]
+    double tm[6] = {1.0, 0.0, 0.0, 1.0, 0.0, 0.0};
+};
+
+} // namespace pdfengine

engine/include/pdfengine/content_stream.hpp

@@ -0,0 +1,35 @@
+#pragma once
+
+#include <string>
+#include <vector>
+
+namespace pdfengine {
+
+/// Result of extracting a raw PDF content stream from a page.
+/// rawContent  — bytes as-found in the PDF (may be compressed)
+/// decodedContent — after applying all /Filter chains (FlateDecode, etc.)
+/// pageIndex   — 0-based page index
+/// filters     — list of filter names applied, e.g. {"FlateDecode"}
+/// compressed  — true if at least one filter was applied
+struct ExtractedStream {
+    std::string rawContent;
+    std::string decodedContent;
+    int         pageIndex   = 0;
+    std::vector<std::string> filters;
+    bool        compressed  = false;
+    bool        multiStream = false;
+};
+
+/// Verifies structural integrity of a decoded content stream.
+/// Returns true if all of: BT, ET, Tf, Tj/TJ are present.
+struct StreamVerification {
+    bool hasBT   = false;
+    bool hasET   = false;
+    bool hasTf   = false;
+    bool hasTj   = false;   // Tj or TJ
+    bool multiStream = false; // page had multiple /Contents streams
+};
+
+StreamVerification verifyContentStream(const ExtractedStream& stream);
+
+} // namespace pdfengine

engine/include/pdfengine/token.hpp

@@ -0,0 +1,35 @@
+#pragma once
+
+#include <string>
+#include <vector>
+#include <cstdint>
+
+namespace pdfengine {
+
+enum class TokenType {
+    Operator,      // e.g., "Tj", "BT", "ET", "Tf", "re", "f"
+    String,        // e.g., "(Hello World)", fully unescaped
+    HexString,     // e.g., "<48656C6C6F>", fully decoded to bytes
+    Name,          // e.g., "/F1" (without the slash, unescaped)
+    Number,        // e.g., "12.3", "-4", stored as string/double
+    ArrayStart,    // "["
+    ArrayEnd,      // "]"
+    DictStart,     // "<<"
+    DictEnd,       // ">>"
+    Boolean,       // "true", "false"
+    Null,          // "null"
+    EndOfStream    // EOF marker
+};
+
+struct Token {
+    TokenType type;
+    std::string stringValue;         // Used for Operator, String, Name
+    std::vector<uint8_t> bytesValue; // Used for HexString
+    double numberValue = 0.0;        // Used for Number
+    
+    // Position tracking for error reporting (optional but helpful)
+    size_t startOffset = 0;
+    size_t endOffset = 0;
+};
+
+} // namespace pdfengine