| Marc Kupietz | 4292bc0 | 2026-03-07 16:12:52 +0100 | [diff] [blame] | 1 | SHELL := /bin/bash |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 2 | SRC_DIR ?= I5 |
| Marc Kupietz | e780732 | 2026-06-05 08:55:41 +0200 | [diff] [blame] | 3 | KORAP_PORT ?= 64543 |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 4 | |
| Marc Kupietz | 9adff67 | 2026-06-09 17:18:17 +0200 | [diff] [blame] | 5 | # Discover all *.i5.xml files in SRC_DIR, excluding inlined tagged copies (*-TAG.i5.xml) |
| 6 | I5_FILES := $(filter-out %-TAG.i5.xml,$(wildcard $(SRC_DIR)/*.i5.xml)) |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 7 | BASENAMES := $(patsubst %.i5.xml,%,$(notdir $(I5_FILES))) |
| 8 | |
| Marc Kupietz | 99ff2b0 | 2026-06-05 08:54:37 +0200 | [diff] [blame] | 9 | # Standard TEI P5 support |
| 10 | TEI_DIR ?= TEI |
| 11 | TEI_FILES := $(wildcard $(TEI_DIR)/*.xml) |
| Marc Kupietz | 3b2f440 | 2026-06-13 10:30:19 +0200 | [diff] [blame] | 12 | # Same files as seen from inside the container (the dir is mounted at /input). |
| 13 | TEI_INPUTS := $(patsubst $(TEI_DIR)/%,/input/%,$(TEI_FILES)) |
| Marc Kupietz | 99ff2b0 | 2026-06-05 08:54:37 +0200 | [diff] [blame] | 14 | TEI_ZIP_NAME ?= tei |
| 15 | TEI_FLAGS ?= --auto-textsigle 'TEI/XYZ.00001' # --xmlid-to-textsigle '([A-Z]+)\.(.*)\.([0-9]+)\.*([0-9])@$$1/$$2/$$3$$4' |
| Marc Kupietz | 99ff2b0 | 2026-06-05 08:54:37 +0200 | [diff] [blame] | 16 | |
| Marc Kupietz | 00db6b0 | 2026-06-11 11:46:23 +0200 | [diff] [blame] | 17 | # If set to a foundry name (e.g. gingko), tei2korapxml will use inline annotations and tokens from the source XML |
| 18 | USE_INLINE_ANNOTATIONS_AS ?= |
| 19 | TEI2KORAPXML_FLAGS ?= $(if $(USE_INLINE_ANNOTATIONS_AS),--no-tokenizer --inline-tokens $(USE_INLINE_ANNOTATIONS_AS),-s -tk) |
| 20 | |
| Marc Kupietz | 99ff2b0 | 2026-06-05 08:54:37 +0200 | [diff] [blame] | 21 | ifneq ($(TEI_FILES),) |
| 22 | BASENAMES += $(TEI_ZIP_NAME) |
| 23 | endif |
| 24 | |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 25 | BUILD_DIR = build |
| Marc Kupietz | 15b313d | 2025-12-11 12:20:56 +0100 | [diff] [blame] | 26 | TARGET_DIR ?= ./target |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 27 | MAX_THREADS ?= 8 # $(shell nproc) |
| 28 | MAKE ?= make -j $(shell nproc) |
| Marc Kupietz | 15b313d | 2025-12-11 12:20:56 +0100 | [diff] [blame] | 29 | # KORAPXMLTOOL_HEAP ?= $(shell echo "$$(($(MAX_THREADS) * 2500))") |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 30 | KORAPXMLTOOL ?= ./bin/korapxmltool |
| Marc Kupietz | 15b313d | 2025-12-11 12:20:56 +0100 | [diff] [blame] | 31 | KORAPXMLTOOL_MODELS_PATH ?= models |
| Marc Kupietz | 4292bc0 | 2026-03-07 16:12:52 +0100 | [diff] [blame] | 32 | DOCKER_CPU_SHARES ?= # e.g. 512 for lower priority (default Docker value is 1024) |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 33 | |
| 34 | .DELETE_ON_ERROR: |
| 35 | |
| Marc Kupietz | 19fa448 | 2026-06-07 15:03:56 +0200 | [diff] [blame] | 36 | .PHONY: all clean test index korap check-src pre-krill krill meta |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 37 | |
| Marc Kupietz | 19fa448 | 2026-06-07 15:03:56 +0200 | [diff] [blame] | 38 | .PRECIOUS: $(BUILD_DIR)/%.zip $(BUILD_DIR)/%.tree_tagger.zip $(BUILD_DIR)/%.marmot-malt.zip $(BUILD_DIR)/%.spacy.zip $(BUILD_DIR)/%.corenlp.zip $(BUILD_DIR)/%.cmc.zip $(BUILD_DIR)/%.opennlp.zip $(BUILD_DIR)/%.meta.xml $(BUILD_DIR)/%.krill.tar %.i5.xml |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 39 | |
| Marc Kupietz | 15b313d | 2025-12-11 12:20:56 +0100 | [diff] [blame] | 40 | all: check-src korap |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 41 | |
| Marc Kupietz | 15b313d | 2025-12-11 12:20:56 +0100 | [diff] [blame] | 42 | index: check-src $(TARGET_DIR)/index |
| 43 | |
| 44 | check-src: |
| Marc Kupietz | 99ff2b0 | 2026-06-05 08:54:37 +0200 | [diff] [blame] | 45 | @if [ ! -d "$(SRC_DIR)" ] && [ ! -d "$(TEI_DIR)" ]; then \ |
| 46 | echo "Error: Neither SRC_DIR '$(SRC_DIR)' nor TEI_DIR '$(TEI_DIR)' exists."; \ |
| 47 | echo "Please place your .i5.xml files in '$(SRC_DIR)' or your TEI .xml files in '$(TEI_DIR)'."; \ |
| Marc Kupietz | 15b313d | 2025-12-11 12:20:56 +0100 | [diff] [blame] | 48 | exit 1; \ |
| 49 | fi |
| Marc Kupietz | 9adff67 | 2026-06-09 17:18:17 +0200 | [diff] [blame] | 50 | @if [ -z "$$(find "$(SRC_DIR)" -maxdepth 1 -name '*.i5.xml' ! -name '*-TAG.i5.xml' -print -quit 2>/dev/null)" ] && \ |
| Marc Kupietz | 99ff2b0 | 2026-06-05 08:54:37 +0200 | [diff] [blame] | 51 | [ -z "$$(find "$(TEI_DIR)" -maxdepth 1 -name '*.xml' -print -quit 2>/dev/null)" ]; then \ |
| 52 | echo "Error: No .i5.xml files found in '$(SRC_DIR)' and no .xml files found in '$(TEI_DIR)'."; \ |
| Marc Kupietz | 15b313d | 2025-12-11 12:20:56 +0100 | [diff] [blame] | 53 | exit 1; \ |
| 54 | fi |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 55 | |
| 56 | $(BUILD_DIR)/%.zip: $(SRC_DIR)/%.i5.xml |
| 57 | mkdir -p $(BUILD_DIR) |
| Marc Kupietz | 00db6b0 | 2026-06-11 11:46:23 +0200 | [diff] [blame] | 58 | docker run --rm -i $(if $(DOCKER_CPU_SHARES),--cpu-shares $(DOCKER_CPU_SHARES)) korap/tei2korapxml:latest -l warn $(TEI2KORAPXML_FLAGS) - < $< > $@ 2> >(tee $(@:.zip=.log) >&2) |
| 59 | # docker run --rm $(if $(DOCKER_CPU_SHARES),--cpu-shares $(DOCKER_CPU_SHARES)) -v $(abspath $<):/input.i5.xml:ro korap/tei2korapxml:latest --progress -l warn $(TEI2KORAPXML_FLAGS) /input.i5.xml > $@ 2> >(tee $(@:.zip=.log) >&2) |
| Marc Kupietz | 4292bc0 | 2026-03-07 16:12:52 +0100 | [diff] [blame] | 60 | printf "%s\t%s\n" "$$(grep -c '<idsText ' $<)" "$$(unzip -l $@ | grep data.xml | wc -l)" |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 61 | |
| Marc Kupietz | 99ff2b0 | 2026-06-05 08:54:37 +0200 | [diff] [blame] | 62 | $(BUILD_DIR)/$(TEI_ZIP_NAME).zip: $(TEI_FILES) |
| 63 | mkdir -p $(BUILD_DIR) |
| Marc Kupietz | 3b2f440 | 2026-06-13 10:30:19 +0200 | [diff] [blame] | 64 | docker run --rm $(if $(DOCKER_CPU_SHARES),--cpu-shares $(DOCKER_CPU_SHARES)) -v "$(abspath $(TEI_DIR)):/input:ro" korap/tei2korapxml:latest -l warn $(TEI2KORAPXML_FLAGS) $(TEI_FLAGS) $(TEI_INPUTS) > $@ 2> >(tee $(@:.zip=.log) >&2) |
| Marc Kupietz | 99ff2b0 | 2026-06-05 08:54:37 +0200 | [diff] [blame] | 65 | printf "%s\t%s\n" "$$(cat $^ | grep -c '<teiHeader')" "$$(unzip -l $@ | grep data.xml | wc -l)" |
| 66 | |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 67 | |
| Marc Kupietz | b820ece | 2026-06-11 14:29:05 +0200 | [diff] [blame] | 68 | $(BUILD_DIR)/%.tree_tagger.zip: $(BUILD_DIR)/%.zip | bin/korapxmltool |
| Marc Kupietz | 5b3ecc0 | 2025-12-15 14:43:09 +0100 | [diff] [blame] | 69 | $(KORAPXMLTOOL) -j 1 -T treetagger -t zip --force -D $(BUILD_DIR) $< |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 70 | # $(KORAPXMLTOOL) $< | pv | docker run --rm -i korap/conllu2treetagger -l german | conllu2korapxml > $@ |
| 71 | |
| Marc Kupietz | b820ece | 2026-06-11 14:29:05 +0200 | [diff] [blame] | 72 | $(BUILD_DIR)/%.spacy.zip: $(BUILD_DIR)/%.zip | bin/korapxmltool |
| Marc Kupietz | 15b313d | 2025-12-11 12:20:56 +0100 | [diff] [blame] | 73 | $(KORAPXMLTOOL) -P spacy -t zip --force -D $(BUILD_DIR) $< |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 74 | |
| Marc Kupietz | 15b313d | 2025-12-11 12:20:56 +0100 | [diff] [blame] | 75 | lib/Krill-Indexer.jar: |
| 76 | mkdir -p lib |
| 77 | curl -sL -o $@ https://github.com/korap/Krill/releases/latest/download/Krill-Indexer.jar |
| Marc Kupietz | 5b3ecc0 | 2025-12-15 14:43:09 +0100 | [diff] [blame] | 78 | |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 79 | bin/korapxmltool: |
| 80 | mkdir -p bin |
| Marc Kupietz | 15b313d | 2025-12-11 12:20:56 +0100 | [diff] [blame] | 81 | curl -sL -o $@ https://github.com/korap/korapxmltool/releases/latest/download/korapxmltool |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 82 | chmod +x $@ |
| 83 | |
| Marc Kupietz | c523981 | 2026-06-05 08:56:46 +0200 | [diff] [blame] | 84 | bin/conllu-gender: |
| 85 | mkdir -p bin |
| 86 | curl -sL -o $@ https://github.com/KorAP/conllu-gender/releases/latest/download/conllu-gender |
| 87 | chmod +x $@ |
| 88 | |
| Marc Kupietz | 15b313d | 2025-12-11 12:20:56 +0100 | [diff] [blame] | 89 | $(KORAPXMLTOOL_MODELS_PATH)/de.marmot: |
| 90 | mkdir -p $(KORAPXMLTOOL_MODELS_PATH) |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 91 | curl -sL -o $@ https://cistern.cis.lmu.de/marmot/models/CURRENT/spmrl/de.marmot |
| 92 | |
| Marc Kupietz | 15b313d | 2025-12-11 12:20:56 +0100 | [diff] [blame] | 93 | $(KORAPXMLTOOL_MODELS_PATH)/german.mco: |
| 94 | mkdir -p $(KORAPXMLTOOL_MODELS_PATH) |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 95 | curl -sL -o $@ https://corpora.ids-mannheim.de/tools/$@ |
| 96 | |
| Marc Kupietz | 15b313d | 2025-12-11 12:20:56 +0100 | [diff] [blame] | 97 | $(KORAPXMLTOOL_MODELS_PATH)/dereko_domains_s.classifier: |
| 98 | mkdir -p $(KORAPXMLTOOL_MODELS_PATH) |
| 99 | curl -sL -o $@ https://corpora.ids-mannheim.de/tools/models/$@ |
| 100 | |
| 101 | $(KORAPXMLTOOL_MODELS_PATH)/german-fast.tagger: |
| 102 | mkdir -p $(KORAPXMLTOOL_MODELS_PATH) |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 103 | curl -sL -o $@ https://corpora.ids-mannheim.de/tools/$@ |
| 104 | |
| Marc Kupietz | 15b313d | 2025-12-11 12:20:56 +0100 | [diff] [blame] | 105 | $(KORAPXMLTOOL_MODELS_PATH)/germanSR.ser.gz: |
| 106 | mkdir -p $(KORAPXMLTOOL_MODELS_PATH) |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 107 | curl -sL -o $@ https://corpora.ids-mannheim.de/tools/$@ |
| 108 | |
| Marc Kupietz | 15b313d | 2025-12-11 12:20:56 +0100 | [diff] [blame] | 109 | $(KORAPXMLTOOL_MODELS_PATH)/de-pos-maxent.bin: |
| 110 | mkdir -p $(KORAPXMLTOOL_MODELS_PATH) |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 111 | curl -sL -o $@ https://corpora.ids-mannheim.de/tools/$@ |
| 112 | |
| Marc Kupietz | b820ece | 2026-06-11 14:29:05 +0200 | [diff] [blame] | 113 | $(BUILD_DIR)/%.marmot-malt.zip: $(BUILD_DIR)/%.zip $(KORAPXMLTOOL_MODELS_PATH)/de.marmot $(KORAPXMLTOOL_MODELS_PATH)/german.mco | bin/korapxmltool |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 114 | $(KORAPXMLTOOL) -T marmot:models/de.marmot -P malt:models/german.mco -t zip --force -D $(BUILD_DIR) $< |
| Marc Kupietz | 5b3ecc0 | 2025-12-15 14:43:09 +0100 | [diff] [blame] | 115 | |
| Marc Kupietz | b820ece | 2026-06-11 14:29:05 +0200 | [diff] [blame] | 116 | $(BUILD_DIR)/%.corenlp.zip: $(BUILD_DIR)/%.zip $(KORAPXMLTOOL_MODELS_PATH)/german-fast.tagger $(KORAPXMLTOOL_MODELS_PATH)/germanSR.ser.gz | bin/korapxmltool |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 117 | $(KORAPXMLTOOL) -T corenlp -P corenlp -t zip --force -D $(BUILD_DIR) $< |
| 118 | |
| Marc Kupietz | b820ece | 2026-06-11 14:29:05 +0200 | [diff] [blame] | 119 | $(BUILD_DIR)/%.opennlp.zip: $(BUILD_DIR)/%.zip $(KORAPXMLTOOL_MODELS_PATH)/de-pos-maxent.bin | bin/korapxmltool |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 120 | $(KORAPXMLTOOL) -T opennlp -t zip --force -D $(BUILD_DIR) $< |
| 121 | |
| Marc Kupietz | b820ece | 2026-06-11 14:29:05 +0200 | [diff] [blame] | 122 | $(BUILD_DIR)/%.cmc.zip: $(BUILD_DIR)/%.zip | bin/korapxmltool |
| Marc Kupietz | 5b3ecc0 | 2025-12-15 14:43:09 +0100 | [diff] [blame] | 123 | $(KORAPXMLTOOL) -j 1 -A "docker run --rm -i korap/conllu-cmc -s" -l error -F cmc -t zip --force -D $(BUILD_DIR) $< |
| Marc Kupietz | 800f9bb | 2025-12-11 17:30:24 +0100 | [diff] [blame] | 124 | |
| Marc Kupietz | b820ece | 2026-06-11 14:29:05 +0200 | [diff] [blame] | 125 | $(BUILD_DIR)/%.gender.zip: $(BUILD_DIR)/%.zip | bin/conllu-gender bin/korapxmltool |
| Marc Kupietz | 463da33 | 2026-03-08 13:19:15 +0100 | [diff] [blame] | 126 | $(KORAPXMLTOOL) -j 1 -A "bin/conllu-gender -s" -l WARNING -F gender -t zip --force -D $(BUILD_DIR) $< |
| Marc Kupietz | a2876eb | 2026-03-07 22:03:17 +0100 | [diff] [blame] | 127 | |
| Marc Kupietz | 19fa448 | 2026-06-07 15:03:56 +0200 | [diff] [blame] | 128 | # --- Stand-off metadata annotations ----------------------------------------- |
| 129 | WIKI_TAXONOMY_IMAGE ?= korap/wiki-taxonomy |
| 130 | |
| Marc Kupietz | ed8cdf0 | 2026-06-09 18:26:22 +0200 | [diff] [blame] | 131 | # Pass --gpus=all to GPU-capable docker runs when a CUDA GPU is usable, detected |
| 132 | # by nvidia-smi succeeding on the host. (The nvidia runtime is not listed in |
| 133 | # `docker info` when the Container Toolkit uses CDI, so we don't probe for it.) |
| Marc Kupietz | 49773a6 | 2026-06-09 17:35:45 +0200 | [diff] [blame] | 134 | # Probed once at parse time; override by setting GPU_FLAG (e.g. GPU_FLAG= to disable). |
| Marc Kupietz | ed8cdf0 | 2026-06-09 18:26:22 +0200 | [diff] [blame] | 135 | GPU_FLAG ?= $(shell if command -v nvidia-smi >/dev/null 2>&1 && nvidia-smi >/dev/null 2>&1; then echo --gpus=all; fi) |
| Marc Kupietz | 49773a6 | 2026-06-09 17:35:45 +0200 | [diff] [blame] | 136 | |
| Marc Kupietz | 19fa448 | 2026-06-07 15:03:56 +0200 | [diff] [blame] | 137 | # Wikipedia top-level topic-domain classification (annotation: wikidomain). |
| 138 | # Unlike the foundry annotations this yields a single stand-off metadata XML per |
| 139 | # corpus, not a per-text zip. The model is baked into the image, so nothing to mount. |
| Marc Kupietz | b820ece | 2026-06-11 14:29:05 +0200 | [diff] [blame] | 140 | $(BUILD_DIR)/%.wikidomain.meta.xml: $(BUILD_DIR)/%.zip | bin/korapxmltool |
| Marc Kupietz | 19fa448 | 2026-06-07 15:03:56 +0200 | [diff] [blame] | 141 | set -o pipefail; $(KORAPXMLTOOL) -t now $< \ |
| Marc Kupietz | 49773a6 | 2026-06-09 17:35:45 +0200 | [diff] [blame] | 142 | | docker run --rm -i $(GPU_FLAG) $(if $(DOCKER_CPU_SHARES),--cpu-shares $(DOCKER_CPU_SHARES)) \ |
| Marc Kupietz | 19fa448 | 2026-06-07 15:03:56 +0200 | [diff] [blame] | 143 | $(WIKI_TAXONOMY_IMAGE) --topk 2 --threshold 0.4 > $@ 2> >(tee $(@:.xml=.log) >&2) |
| 144 | |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 145 | # udpipe target removed as requested |
| 146 | # %.ud.zip: %.zip |
| 147 | # $(KORAPXMLTOOL) $< | pv | ./scripts/udpipe2 | conllu2korapxml > $@ |
| 148 | |
| Marc Kupietz | 19fa448 | 2026-06-07 15:03:56 +0200 | [diff] [blame] | 149 | # Active annotation layers to run and package into Krill. Most produce a per-text |
| 150 | # foundry zip; those also listed in META_ANNOTATIONS instead produce a single |
| 151 | # stand-off metadata XML per corpus (auto-detected by korapxmltool). |
| 152 | ANNOTATIONS ?= marmot-malt tree_tagger spacy corenlp opennlp wikidomain |
| 153 | META_ANNOTATIONS ?= wikidomain |
| Marc Kupietz | c523981 | 2026-06-05 08:56:46 +0200 | [diff] [blame] | 154 | |
| Marc Kupietz | 19fa448 | 2026-06-07 15:03:56 +0200 | [diff] [blame] | 155 | # Build artifact produced by annotation $(2) for base $(1): a stand-off .meta.xml |
| 156 | # for meta-type annotations, otherwise a foundry .zip. |
| 157 | artifact = $(BUILD_DIR)/$(1).$(2).$(if $(filter $(2),$(META_ANNOTATIONS)),meta.xml,zip) |
| 158 | # Meta-type annotations that are actually active (must be passed to krill explicitly, |
| 159 | # since the recipe globs *.zip only). |
| 160 | ACTIVE_META := $(filter $(META_ANNOTATIONS),$(ANNOTATIONS)) |
| 161 | |
| 162 | KRILL_PREREQS := $(foreach base,$(BASENAMES),$(BUILD_DIR)/$(base).zip $(foreach ann,$(ANNOTATIONS),$(call artifact,$(base),$(ann)))) |
| Marc Kupietz | 4292bc0 | 2026-03-07 16:12:52 +0100 | [diff] [blame] | 163 | |
| 164 | pre-krill: check-src $(KRILL_PREREQS) |
| 165 | |
| Marc Kupietz | 19fa448 | 2026-06-07 15:03:56 +0200 | [diff] [blame] | 166 | # Build just the stand-off metadata layers without indexing. |
| 167 | meta: check-src $(foreach base,$(BASENAMES),$(foreach ann,$(ACTIVE_META),$(BUILD_DIR)/$(base).$(ann).meta.xml)) |
| 168 | |
| 169 | # The base zip, every annotation zip, and every stand-off meta XML are folded into |
| 170 | # one Krill tar. korapxmltool auto-detects the .meta.xml stand-off inputs. |
| Marc Kupietz | b820ece | 2026-06-11 14:29:05 +0200 | [diff] [blame] | 171 | $(BUILD_DIR)/%.krill.tar: $(BUILD_DIR)/%.zip $(foreach ann,$(ANNOTATIONS),$(call artifact,%,$(ann))) | bin/korapxmltool |
| Marc Kupietz | 19fa448 | 2026-06-07 15:03:56 +0200 | [diff] [blame] | 172 | $(KORAPXMLTOOL) --non-word-tokens -f -t krill -D $(BUILD_DIR) $(basename $<)*.zip $(foreach ann,$(ACTIVE_META),$(BUILD_DIR)/$*.$(ann).meta.xml) |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 173 | |
| Marc Kupietz | 463da33 | 2026-03-08 13:19:15 +0100 | [diff] [blame] | 174 | krill: $(foreach base,$(BASENAMES),$(BUILD_DIR)/$(base).krill.tar) |
| 175 | |
| Marc Kupietz | 15b313d | 2025-12-11 12:20:56 +0100 | [diff] [blame] | 176 | $(TARGET_DIR)/index: $(foreach base,$(BASENAMES),$(BUILD_DIR)/$(base).krill.tar) |
| 177 | make lib/Krill-Indexer.jar |
| 178 | touch lib/krill.cfg |
| 179 | mkdir -p $(TARGET_DIR) |
| 180 | java -jar lib/Krill-Indexer.jar -c lib/krill.cfg --progress -i $(subst " ",;,$^) -o $@ |
| 181 | |
| 182 | korap: check-src $(TARGET_DIR)/index |
| Marc Kupietz | 20b2d1d | 2026-06-15 12:25:37 +0200 | [diff] [blame^] | 183 | curl -s https://raw.githubusercontent.com/KorAP/KorAP-Docker/master/compose.yaml | sed 's/64543:64543/$(KORAP_PORT):64543/g' | COMPOSE_PROFILES='export,open,lite' INDEX='$(TARGET_DIR)/index' docker compose -p korap -f - up |
| Marc Kupietz | 89a4407 | 2025-12-11 07:14:00 +0100 | [diff] [blame] | 184 | |
| 185 | $(TARGET_DIR)/index.tar.xz: $(TARGET_DIR)/index |
| 186 | tar -I 'xz -T0' -C $(dir $<) -cf $@ $(notdir $<) |
| 187 | |
| 188 | clean: |
| 189 | rm -rf $(BUILD_DIR) $(TARGET_DIR) |