@thedecipherist/mdd 1.5.0 → 1.5.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/commands/mdd-import-spec.md +27 -2
- package/package.json +1 -1
|
@@ -12,9 +12,34 @@ Parse file path(s) from the arguments following `import-spec`. Multiple files ma
|
|
|
12
12
|
|
|
13
13
|
For each file path:
|
|
14
14
|
1. Verify the file exists. If a path does not exist, stop and report clearly: "File not found: `<path>`"
|
|
15
|
-
2.
|
|
15
|
+
2. Count the file's lines: `wc -l <path>`
|
|
16
|
+
3. Read the full content using the strategy below.
|
|
16
17
|
|
|
17
|
-
|
|
18
|
+
**Reading strategy — always read the full file, never stop early:**
|
|
19
|
+
|
|
20
|
+
Files under 2,000 lines: read in a single call.
|
|
21
|
+
|
|
22
|
+
Files over 2,000 lines: read in sequential chunks of 2,000 lines each.
|
|
23
|
+
|
|
24
|
+
```
|
|
25
|
+
chunk 1: offset 0, limit 2000
|
|
26
|
+
chunk 2: offset 2000, limit 2000
|
|
27
|
+
chunk 3: offset 4000, limit 2000
|
|
28
|
+
... continue until offset >= total line count
|
|
29
|
+
```
|
|
30
|
+
|
|
31
|
+
After each chunk, append its headings and content to a running working document. Do not begin IS2 analysis until the final chunk has been read and the full working document is assembled. Report progress as you read:
|
|
32
|
+
|
|
33
|
+
```
|
|
34
|
+
Reading <filename> (<N> lines)...
|
|
35
|
+
chunk 1/N (lines 1–2000) ✓
|
|
36
|
+
chunk 2/N (lines 2001–4000) ✓
|
|
37
|
+
...
|
|
38
|
+
chunk N/N (lines <X>–<end>) ✓
|
|
39
|
+
Full file read. Proceeding to feature extraction.
|
|
40
|
+
```
|
|
41
|
+
|
|
42
|
+
If multiple files are provided, merge all content into a single working document after all files are fully read. Tag each section internally with its source filename (e.g. `<!-- source: rawpg-prompt-driver.md -->`) for traceability — these tags are used in the merge summary and content mapping display but are never written to output docs.
|
|
18
43
|
|
|
19
44
|
---
|
|
20
45
|
|