Naive text extraction against structure-preserving extraction
The same page, the same PDF bytes, extracted twice just now. On the left,
pypdfium2 emitting the text in content-stream order, which is what most ingestion
pipelines do. On the right, pdfplumber word boxes with our own layout logic:
ruled-line and column-gap table detection, heading detection, and a Markdown rendering that
keeps the cell grid.
Naive: pypdfium2.get_text_range()
6217 characters, no structure at all
FIST Volume 4-1A Maintenance Scheduling for Mechanical Equipment (FIST 016) 07/27/2020 NEW RELEASE v 2.5.1 Packing ............................................................................................................................45 2.5.2 Mechanical Seals.............................................................................................................46 2.6 Bearings ..............................................................................................................................47 2.6.1 Fluid Film Bearings .......................................................................................................47 2.6.2 Antifriction Bearings.....................................................................................................47 2.7 Shaft Couplings .................................................................................................................47 2.8 Shaft Alignment.................................................................................................................48 2.8.1 Horizontal Pump Alignment........................................................................................48 2.8.2 Face and Rim Alignment Method ...............................................................................50 2.8.3 Reverse Indicator Method............................................................................................55 2.9 Vibration Monitoring and Analysis................................................................................59 2.9.1 Proximity Probe Systems..............................................................................................59 2.9.2 Accelerometer Systems.................................................................................................60 2.9.3 Signature Analysis..........................................................................................................60 2.10 Oil and Lubricants ............................................................................................................61 2.10.1 Oil Lubrication...............................................................................................................62 2.10.2 Grease Lubrication ........................................................................................................62 2.10.3 Hydraulic Oil ..................................................................................................................63 2.10.4 Testing and Filtering......................................................................................................63 2.11 Inspection Checklist..........................................................................................................64 2.11.1 Hydraulic Turbines and Large Pumps........................................................................66 2.11.2 Auxiliary Pumps.............................................................................................................69 Penstocks, Outlet Pipes, Piping, Gates, and Valves..................................................... 71 3.1 Penstocks, Outlet Pipes, Lines, and Piping...................................................................71 3.2 Gates and Valves...............................................................................................................71 3.2.1 General ............................................................................................................................71 3.2.2 Gates................................................................................................................................75 3.2.3 Valves...............................................................................................................................87 3.2.4 Valve and Gate Operators............................................................................................91 3.3 Guard Gate and Valve Closure Tests.............................................................................98 3.4 Turbine Pressure Relief Valves.......................................................................................99 3.5 Auxiliary Piping Systems..................................................................................................99 3.6 Inspection Checklist....................................................................................................... 100 3.6.1 Gates and Valves......................................................................................................... 100 3.6.2 Penstocks, Outlet Pipes............................................................................................. 102 3.6.3 Gates and Valves......................................................................................................... 103 3.6.4 Gate and Valve Operators and Hoists..................................................................... 105 3.6.5 Guard Gate and Valve Closure Tests...................................................................... 107 3.6.6 Turbine Pressure Relief Valves Operational Tests................................................ 107 3.6.7 Auxiliary Piping Systems............................................................................................ 107 Governors ...................................................................................................................... 109 Air Compressors ........................................................................................................... 110 5.1 General............................................................................................................................. 110 5.2 Reciprocating Air Compressors................................................................................... 110 5.3 Rotary Screw Air Compressors.................................................................................... 110 5.4 Accessories...................................................................................................................... 111 5.4.1 Inlet Filters................................................................................................................... 111
Structure-preserving: pdfplumber + layout logic
3 blocks, 1 table(s) recovered
| | | | | FIST Vo | lume 4-1A | |---|---|---|---|---|---| | | | | Mainte | nance Scheduling for Mechanical | Equipment | | | 2.5.1 Packing | ................. | ....................... | ................................................................... | ................. 45 | | | 2.5.2 Mechani | cal Seals.. | ....................... | ................................................................... | ................. 46 | | 2.6 | Bearings .. | ................. | ....................... | ................................................................... | ................. 47 | | | 2.6.1 Fluid Fil | m Bearin | gs ................... | ................................................................... | ................. 47 | | | 2.6.2 Antifrict | ion Beari | ngs ................. | ................................................................... | ................. 47 | | 2.7 | Shaft Cou | plings ...... | ....................... | ................................................................... | ................. 47 | | 2.8 | Shaft Alig | nment ...... | ....................... | ................................................................... | ................. 48 | | | 2.8.1 Horizon | tal Pump | Alignment .... | ................................................................... | ................. 48 | | | 2.8.2 Face and | Rim Ali | gnment Meth | od .............................................................. | ................. 50 | | | 2.8.3 Reverse | Indicator | Method ........ | ................................................................... | ................. 55 | | 2.9 | Vibration | Monitori | ng and Analys | is ............................................................... | ................. 59 | | | 2.9.1 Proximit | y Probe S | ystems .......... | ................................................................... | ................. 59 | | | 2.9.2 Accelero | meter Sy | stems ............. | ................................................................... | ................. 60 | | | 2.9.3 Signatur | e Analysis | ...................... | ................................................................... | ................. 60 | | 2.10 | Oil and Lu | bricants . | ....................... | ................................................................... | ................. 61 | | | 2.10.1 Oil Lubr | ication .... | ....................... | ................................................................... | ................. 62 | | | 2.10.2 Grease L | ubricatio | n .................... | ................................................................... | ................. 62 | | | 2.10.3 Hydrauli | c Oil ....... | ....................... | ................................................................... | ................. 63 | | | 2.10.4 Testing | and Filter | ing .................. | ................................................................... | ................. 63 | | 2.11 | Inspection | Checklis | t...................... | ................................................................... | ................. 64 | | | 2.11.1 Hydrauli | c Turbin | es and Large | Pumps ....................................................... | ................. 66 | | | 2.11.2 Auxiliary | Pumps .. | ....................... | ................................................................... | ................. 69 | | Pen | stocks, Outlet | Pipes, Pi | ping, Gates, | and Valves ....................................... | .............. 71 | | 3.1 | Penstocks, | Outlet P | ipes, Lines, a | nd Piping .................................................. | ................. 71 | | 3.2 | Gates and | Valves .... | ....................... | ................................................................... | ................. 71 | | | 3.2.1 General | ................. | ....................... | ................................................................... | ................. 71 | | | 3.2.2 Gates .... | ................. | ....................... | ................................................................... | ................. 75 | | | 3.2.3 Valves... | ................. | ....................... | ................................................................... | ................. 87 | | | 3.2.4 Valve an | d Gate O | perators ........ | ................................................................... | ................. 91 | | 3.3 | Guard Ga | te and Va | lve Closure T | ests ............................................................ | ................. 98 | | 3.4 | Turbine P | ressure R | elief Valves ... | ................................................................... | ................. 99 | | 3.5 | Auxiliary P | iping Sys | tems .............. | ................................................................... | ................. 99 | | 3.6 | Inspection | Checklis | t...................... | ................................................................... | .............. 100 | | | 3.6.1 Gates an | d Valves . | ....................... | ................................................................... | .............. 100 | | | 3.6.2 Penstoc | ks, Outlet | Pipes ............ | ................................................................... | .............. 102 | | | 3.6.3 Gates an | d Valves . | ....................... | ................................................................... | .............. 103 | | | 3.6.4 Gate an | d Valve O | perators and | Hoists ....................................................... | .............. 105 | | | 3.6.5 Guard G | ate and | Valve Closure | Tests ........................................................ | .............. 107 | | | 3.6.6 Turbine | Pressure | Relief Valves | Operational Tests .................................. | .............. 107 | | | 3.6.7 Auxiliary | Piping S | ystems ........... | ................................................................... | .............. 107 | | Go | vernors ............ | ............... | .................... | ........................................................... | ............ 109 | | Air | Compressors . | ............... | .................... | ........................................................... | ............ 110 | | 5.1 | General .... | ................. | ....................... | ................................................................... | .............. 110 | | 5.2 | Reciprocat | ing Air C | ompressors .. | ................................................................... | .............. 110 | | 5.3 | Rotary Scr | ew Air C | ompressors ... | ................................................................... | .............. 110 | | 5.4 | Accessorie | s .............. | ....................... | ................................................................... | .............. 111 | | | 5.4.1 Inlet Filt | ers ........... | ....................... | ................................................................... | .............. 111 | | 16) | 07/27/2020 | | | | | | ELE | ASE | | | | v | (FIST 016) ### NEW RELEASE
Read the left column as a retrieval unit
The cell values are all present on the left. What is missing is which row and which column each
one belongs to. An interval table extracted that way produces chunks that contain the right
numbers attached to the wrong tasks, and no amount of prompt engineering downstream can put the
grid back.
The recovered table
| | | | | FIST Vo | lume 4-1A | |---|---|---|---|---|---| | | | | Mainte | nance Scheduling for Mechanical | Equipment | | | 2.5.1 Packing | ................. | ....................... | ................................................................... | ................. 45 | | | 2.5.2 Mechani | cal Seals.. | ....................... | ................................................................... | ................. 46 | | 2.6 | Bearings .. | ................. | ....................... | ................................................................... | ................. 47 | | | 2.6.1 Fluid Fil | m Bearin | gs ................... | ................................................................... | ................. 47 | | | 2.6.2 Antifrict | ion Beari | ngs ................. | ................................................................... | ................. 47 | | 2.7 | Shaft Cou | plings ...... | ....................... | ................................................................... | ................. 47 | | 2.8 | Shaft Alig | nment ...... | ....................... | ................................................................... | ................. 48 | | | 2.8.1 Horizon | tal Pump | Alignment .... | ................................................................... | ................. 48 | | | 2.8.2 Face and | Rim Ali | gnment Meth | od .............................................................. | ................. 50 | | | 2.8.3 Reverse | Indicator | Method ........ | ................................................................... | ................. 55 | | 2.9 | Vibration | Monitori | ng and Analys | is ............................................................... | ................. 59 | | | 2.9.1 Proximit | y Probe S | ystems .......... | ................................................................... | ................. 59 | | | 2.9.2 Accelero | meter Sy | stems ............. | ................................................................... | ................. 60 | | | 2.9.3 Signatur | e Analysis | ...................... | ................................................................... | ................. 60 | | 2.10 | Oil and Lu | bricants . | ....................... | ................................................................... | ................. 61 | | | 2.10.1 Oil Lubr | ication .... | ....................... | ................................................................... | ................. 62 | | | 2.10.2 Grease L | ubricatio | n .................... | ................................................................... | ................. 62 | | | 2.10.3 Hydrauli | c Oil ....... | ....................... | ................................................................... | ................. 63 | | | 2.10.4 Testing | and Filter | ing .................. | ................................................................... | ................. 63 | | 2.11 | Inspection | Checklis | t...................... | ................................................................... | ................. 64 | | | 2.11.1 Hydrauli | c Turbin | es and Large | Pumps ....................................................... | ................. 66 | | | 2.11.2 Auxiliary | Pumps .. | ....................... | ................................................................... | ................. 69 | | Pen | stocks, Outlet | Pipes, Pi | ping, Gates, | and Valves ....................................... | .............. 71 | | 3.1 | Penstocks, | Outlet P | ipes, Lines, a | nd Piping .................................................. | ................. 71 | | 3.2 | Gates and | Valves .... | ....................... | ................................................................... | ................. 71 | | | 3.2.1 General | ................. | ....................... | ................................................................... | ................. 71 | | | 3.2.2 Gates .... | ................. | ....................... | ................................................................... | ................. 75 | | | 3.2.3 Valves... | ................. | ....................... | ................................................................... | ................. 87 | | | 3.2.4 Valve an | d Gate O | perators ........ | ................................................................... | ................. 91 | | 3.3 | Guard Ga | te and Va | lve Closure T | ests ............................................................ | ................. 98 | | 3.4 | Turbine P | ressure R | elief Valves ... | ................................................................... | ................. 99 | | 3.5 | Auxiliary P | iping Sys | tems .............. | ................................................................... | ................. 99 | | 3.6 | Inspection | Checklis | t...................... | ................................................................... | .............. 100 | | | 3.6.1 Gates an | d Valves . | ....................... | ................................................................... | .............. 100 | | | 3.6.2 Penstoc | ks, Outlet | Pipes ............ | ................................................................... | .............. 102 | | | 3.6.3 Gates an | d Valves . | ....................... | ................................................................... | .............. 103 | | | 3.6.4 Gate an | d Valve O | perators and | Hoists ....................................................... | .............. 105 | | | 3.6.5 Guard G | ate and | Valve Closure | Tests ........................................................ | .............. 107 | | | 3.6.6 Turbine | Pressure | Relief Valves | Operational Tests .................................. | .............. 107 | | | 3.6.7 Auxiliary | Piping S | ystems ........... | ................................................................... | .............. 107 | | Go | vernors ............ | ............... | .................... | ........................................................... | ............ 109 | | Air | Compressors . | ............... | .................... | ........................................................... | ............ 110 | | 5.1 | General .... | ................. | ....................... | ................................................................... | .............. 110 | | 5.2 | Reciprocat | ing Air C | ompressors .. | ................................................................... | .............. 110 | | 5.3 | Rotary Scr | ew Air C | ompressors ... | ................................................................... | .............. 110 | | 5.4 | Accessorie | s .............. | ....................... | ................................................................... | .............. 111 | | | 5.4.1 Inlet Filt | ers ........... | ....................... | ................................................................... | .............. 111 | | 16) | 07/27/2020 | | | | | | ELE | ASE | | | | v |
51 rows × 6 columns
Data quality: the text layer we were given
This page's naive text scores 0.99 on a crude legibility measure
(junk-character ratio 0.000, single-character orphan tokens
0.004). The Internet Archive microfiche scans carry a 1990s OCR layer, and
it is wrong in ways that matter: the Stewart-Warner cover reads
TM 59-4310 -275-14 for TM 5-4310-275-14, 4 CFM, 3000 PS! for PSI, and
JUNE 1935 for June 1975. That is not a defect in this demonstration; it is what a
scanned service archive is, and it is the reason exact model-string matching cannot be the only
variant guard.
| Document | Source | OCR score | Pages | Tables | Observed misreads |
|---|---|---|---|---|---|
| TM 9-4310-241-35P — Champion LP-512-ENG / LP-512-ENG-1 / OEH-34-60-ENG | scanned-microfiche | 0.42 | 91 | 16 | PSI misread ×3, pipe/bang inside a word ×2, l/I/1 confusion ×12 |
| TM 5-4310-277-25P — Champion Pneumatic HGR5-8M-1 and BGR-5M-1, 15 CFM | scanned-microfiche | 0.52 | 104 | 55 | PSI misread ×9, pipe/bang inside a word ×14, l/I/1 confusion ×24 |
| TM 3-1040-244-35P — Compressor, Reciprocating, Power-Driven, Flamethro | scanned-microfiche | 0.54 | 77 | 35 | pipe/bang inside a word ×6, l/I/1 confusion ×12, letter-spaced fragmentation ×3 |
| TM 5-4310-227-34P — Champion Pneumatic OEG-458-ENG-1/-2/-3 and BMW-452 | scanned-microfiche | 0.60 | 114 | 41 | PSI misread ×1, pipe/bang inside a word ×4, l/I/1 confusion ×11 |
| TM 5-4310-277-14 — Champion Pneumatic HGR5-8M-1 (tank mounted) and BGR | scanned-microfiche | 0.64 | 139 | 4 | PSI misread ×9, pipe/bang inside a word ×3, l/I/1 confusion ×16 |
| TM 3-4310-100-20&P — Compressor Unit, Reciprocating, Power-Driven, Fla | scanned-microfiche | 0.64 | 51 | 6 | PSI misread ×1, TM number mangled ×6, pipe/bang inside a word ×1 |
| TM 3-4310-100-20&P — alternate scan of the same manual (near-duplicate | scanned-microfiche | 0.65 | 57 | 0 | TM number mangled ×4, pipe/bang inside a word ×1, l/I/1 confusion ×10 |
| TM 9-4310-241-15 — Compressor, Reciprocating, Air, 5 CFM 175 PSI (Cham | scanned-microfiche | 0.65 | 132 | 6 | PSI misread ×15, pipe/bang inside a word ×1, l/I/1 confusion ×26 |
| TM 5-4310-378-14 — Compressor Unit, Reciprocating, 5 CFM 175 PSI, gaso | scanned-microfiche | 0.66 | 154 | 4 | PSI misread ×4, pipe/bang inside a word ×1, l/I/1 confusion ×15 |
| TM 5-4310-221-15 — Ingersoll-Rand GER-125, rotary, skid mounted, gasol | scanned-microfiche | 0.66 | 212 | 8 | PSI misread ×9, l/I/1 confusion ×43, letter-spaced fragmentation ×4 |
| TM 9-4310-227-15 — Compressor, Reciprocating, Air, gasoline engine dri | scanned-microfiche | 0.66 | 170 | 7 | PSI misread ×4, pipe/bang inside a word ×3, l/I/1 confusion ×19 |
| TM 5-4310-339-15 — Compressor, Reciprocating, Air, 15 CFM 175 PSI, ele | scanned-microfiche | 0.66 | 55 | 1 | PSI misread ×4, l/I/1 confusion ×12 |
| TM 5-4310-363-14 — Bauer KAB-545-15, 15 CFM 175 PSI, tank mounted, GED | scanned-microfiche | 0.67 | 130 | 9 | PSI misread ×9, l/I/1 confusion ×19, letter-spaced fragmentation ×1 |
| TM 5-4310-275-14 — Stewart-Warner 43040-301-01, reciprocating, GED, 2- | scanned-microfiche | 0.67 | 122 | 4 | PSI misread ×4, TM number mangled ×2, l/I/1 confusion ×21 |
| TM 5-4310-360-14 — Compressor, Reciprocating, Air, hand-truck mounted, | scanned-microfiche | 0.67 | 92 | 8 | PSI misread ×1, TM number mangled ×1, l/I/1 confusion ×19 |
| TM 5-4310-354-14 — Davey 6M125, rotary, skid mounted, diesel, 125 CFM | scanned-microfiche | 0.67 | 316 | 14 | PSI misread ×25, pipe/bang inside a word ×2, l/I/1 confusion ×22 |
| FIST 4-1A Rev 3.0 — Maintenance Scheduling for Mechanical Equipment | born-digital | 0.69 | 200 | 55 | l/I/1 confusion ×45 |
| FIST 4-1A (May 2024) — Maintenance Scheduling for Mechanical Equipment | born-digital | 0.69 | 208 | 66 | l/I/1 confusion ×46 |
| FIST 4-1A (Jul 2020) — Maintenance Scheduling for Mechanical Equipment | born-digital | 0.69 | 222 | 52 | l/I/1 confusion ×46 |
| FIST 1-1 — Hazardous Energy Control Program (lockout/tagout) | born-digital | 0.69 | 97 | 2 | l/I/1 confusion ×25 |
| Improving Compressed Air System Performance — Compressed Air Challenge | born-digital | 0.72 | 114 | 3 | l/I/1 confusion ×12, letter-spaced fragmentation ×1 |
| Improving Compressed Air System Performance: A Sourcebook for Industry | born-digital | 0.72 | 114 | 3 | l/I/1 confusion ×12, letter-spaced fragmentation ×1 |
| FIST 2-9 — Inspection of Unfired Pressure Vessels | born-digital | 0.75 | 41 | 5 | l/I/1 confusion ×12 |
| FIST 2-6 — Maintenance of Auxiliary Mechanical Equipment | born-digital | 0.84 | 86 | 1 | l/I/1 confusion ×8 |
| FIST 2-4 — Lubrication of Equipment | born-digital | 0.95 | 48 | 6 | l/I/1 confusion ×1 |
Index built by scripts/build_index.py at 2026-08-10 01:44:34 in 711s: 25 documents, 3,146 pages, 12,590 improved chunks / 5,434 naive chunks. Embeddings: Snowflake/snowflake-arctic-embed-s (int8 ONNX, Apache-2.0). Reranker: cross-encoder/ms-marco-MiniLM-L-6-v2 (ONNX, Apache-2.0).