xenia-analysis: unify disasm via xenia-cpu, split ingest/analyze, add sinks

The old src/ppc.rs that re-implemented PPC formatting collapses into
a 30-line shim that delegates to xenia-cpu's single-source-of-truth
disasm. A new disasm.rs wraps the shared iterator and feeds enriched
items (analysis context: function membership, xrefs, mnemonics) into
pluggable sinks.

Sinks split: text.rs (objdump-like output), json.rs (JSONL stream
matching the new xenia dis --json mode), duckdb.rs (the analysis DB
ingest). db.rs is restructured into ingest_instructions +
write_analysis_results so a run can stop after raw ingest, and a new
target_hex column lands on the instructions table. sql_views.rs adds
five additive views layered on top of the raw tables.

Tests: assert-based JSON-fixture goldens (disasm_goldens) and a
PRAGMA-table_info schema golden (db_schema_golden) covering all
ingested tables and the SQL views.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
MechaCat02
2026-05-01 16:28:06 +02:00
parent c36cca14f9
commit 45e15d7885
15 changed files with 1194 additions and 1757 deletions

View File

@@ -0,0 +1,37 @@
//! DuckDB sink — appends rich disasm items to the `instructions` table.
//!
//! Column layout matches [`crate::db`]: address, raw, mnemonic, operands,
//! disasm, ext_mnemonic, ext_operands, ext_disasm, section, function, label.
use duckdb::{Appender, params};
use crate::disasm::RichDisasmItem;
/// Append every item to the appender. Returns the number of rows written.
/// Does NOT flush — the caller decides when to flush, since multiple
/// section iterators typically share one appender.
pub fn append_instructions<'a>(
appender: &mut Appender<'_>,
items: impl IntoIterator<Item = RichDisasmItem<'a>>,
) -> duckdb::Result<u64> {
let mut count: u64 = 0;
for ri in items {
let t = &ri.item.text;
appender.append_row(params![
ri.item.addr as i64,
ri.item.raw as i64,
t.mnemonic.as_str(),
t.operands.as_str(),
t.disasm.as_str(),
t.ext_mnemonic.as_deref(),
t.ext_operands.as_deref(),
t.ext_disasm.as_deref(),
t.branch_target.map(|t| t as i64),
ri.section,
ri.function.map(|f| f as i64),
ri.label,
])?;
count += 1;
}
Ok(count)
}

View File

@@ -0,0 +1,63 @@
//! JSON Lines sink — one structured row per line, constant memory.
//!
//! Suited for piping into `jq`, importing into pandas / DuckDB's
//! `read_json_auto`, or feeding downstream tooling that expects a
//! line-delimited stream rather than a single megaobject.
use std::io::{self, Write};
use serde::Serialize;
use crate::disasm::RichDisasmItem;
#[derive(Serialize)]
struct JsonRow<'a> {
addr: u32,
raw: u32,
mnemonic: &'a str,
operands: &'a str,
disasm: &'a str,
#[serde(skip_serializing_if = "Option::is_none")]
ext_mnemonic: Option<&'a str>,
#[serde(skip_serializing_if = "Option::is_none")]
ext_operands: Option<&'a str>,
#[serde(skip_serializing_if = "Option::is_none")]
ext_disasm: Option<&'a str>,
#[serde(skip_serializing_if = "Option::is_none")]
branch_target: Option<u32>,
section: &'a str,
#[serde(skip_serializing_if = "Option::is_none")]
function: Option<u32>,
#[serde(skip_serializing_if = "Option::is_none")]
label: Option<&'a str>,
}
/// Write each item as a single JSON object on its own line. Returns the
/// number of rows written.
pub fn write_jsonl<'a, W: Write>(
out: &mut W,
items: impl IntoIterator<Item = RichDisasmItem<'a>>,
) -> io::Result<u64> {
let mut count: u64 = 0;
for ri in items {
let t = &ri.item.text;
let row = JsonRow {
addr: ri.item.addr,
raw: ri.item.raw,
mnemonic: &t.mnemonic,
operands: &t.operands,
disasm: &t.disasm,
ext_mnemonic: t.ext_mnemonic.as_deref(),
ext_operands: t.ext_operands.as_deref(),
ext_disasm: t.ext_disasm.as_deref(),
branch_target: t.branch_target,
section: ri.section,
function: ri.function,
label: ri.label,
};
serde_json::to_writer(&mut *out, &row)?;
out.write_all(b"\n")?;
count += 1;
}
Ok(count)
}

View File

@@ -0,0 +1,8 @@
//! Output sinks for [`crate::disasm::RichDisasmItem`] streams.
//!
//! Each sink consumes the same iterator shape and writes to a different
//! medium: human-readable .asm text, JSON Lines, or DuckDB rows.
pub mod duckdb;
pub mod json;
pub mod text;

View File

@@ -0,0 +1,58 @@
//! Text sink — renders one .asm instruction line with optional
//! branch-target / data-ref annotations.
//!
//! The full `write_asm` orchestration (section headers, function prologue
//! info, xref comment blocks, hex-dump of data sections) stays in
//! [`crate::formatter`]; this sink only owns the per-instruction line.
use std::collections::HashMap;
use std::io::{self, Write};
use xenia_xex::pe::PeSection;
use crate::disasm::RichDisasmItem;
use crate::xref::{XrefKind, section_for_addr};
/// Render one instruction line:
/// ` 82000000: 60000000 nop`
/// ` 82000004: 4800FFFC bl 0x82000000 ; -> entry_point`
/// ` 82000010: 812A0000 lwz r9, 0(r10) ; [R] 0x828A0000 (.rdata) = dat_…`
pub fn write_instr_line<W: Write + ?Sized>(
out: &mut W,
item: &RichDisasmItem<'_>,
labels: &HashMap<u32, String>,
sections: &[PeSection],
image_base: u32,
data_annotation: Option<(u32, XrefKind)>,
) -> io::Result<()> {
let disasm_text = item.item.text.display();
// Branch-target → label annotation. Uses the structured `branch_target`
// field (cleaner than the legacy "find 0x in disasm string" regex).
let mut annotated = match item.item.text.branch_target {
Some(target) => match labels.get(&target) {
Some(lbl) => format!("{disasm_text:<40} ; -> {lbl}"),
None => disasm_text.to_string(),
},
None => disasm_text.to_string(),
};
if let Some((data_addr, kind)) = data_annotation {
let tag = match kind {
XrefKind::DataRead => "[R]",
XrefKind::DataWrite => "[W]",
_ => "[&]",
};
let sec = section_for_addr(data_addr, sections, image_base).unwrap_or("?");
let data_lbl = labels.get(&data_addr)
.map(|s| format!(" = {s}"))
.unwrap_or_default();
if !annotated.contains("; ->") {
annotated = format!("{annotated:<40} ; {tag} 0x{data_addr:08X} ({sec}){data_lbl}");
} else {
annotated = format!("{annotated} {tag} 0x{data_addr:08X} ({sec}){data_lbl}");
}
}
writeln!(out, " {:08X}: {:08X} {}", item.item.addr, item.item.raw, annotated)
}