Improve export-file.sh script and add docs

2025-05-29 03:29:14 +00:00 · 2020-11-30 00:59:24 +01:00 · 2020-11-30 00:59:24 +01:00 · 8c8dd2fb40
commit 8c8dd2fb40
parent 0dafe57034
3 changed files with 256 additions and 17 deletions
--- a/tools/export-files.sh
+++ b/tools/export-files.sh
@ -5,8 +5,13 @@
 # (the original files).
 #
 # The item's metadata are stored next to the files to provide more
-# information about the item. It is not meant to be imported back into
-# docspell.
+# information about the item: tags, dates, custom fields etc. This
+# contains most of your user supplied data.
+#
+# This script is intended for having your data outside and independent
+# of docspell. Another good idea for a backup strategy is to take
+# database dumps *and* storing the releases of docspell next to this
+# dump.
 #
 # Usage:
 #
@ -19,8 +24,29 @@
 #
 #    export-files.sh http://localhost:7880 /tmp/ds-download
 #
+# The script then asks for username and password and starts
+# downloading. Files are downloaded into the following structure
+# (below the given target directory):
 #
-# The script then asks for username and password and starts downloading.
+# - yyyy-mm (item date)
+#   - A3…XY (item id)
+#     - somefile.pdf (attachments with name)
+#     - metadata.json (json file with items metadata)
+#
+# By default, files are not overwritten, it stops if existing files
+# are encountered. Configuration can be specified using environment
+# variables:
+#
+# - OVERWRITE_FILE= if `y` then overwriting existing files is ok.
+# - SKIP_FILE= if `y` then existing files are skipped (supersedes
+#   OVERWRITE_FILE).
+# - DROP_ITEM= if `y` the item folder is removed before attempting to
+#   download it. If this is set to `y` then the above options don't
+#   make sense, since they operate on the files inside the item folder
+#
+# Docspell sends with each file its sha256 checksum via the ETag
+# header. This is used to do a integrity check after downloading.
+

 if [ -z "$1" ]; then
    echo "The base-url to docspell is required."
@ -41,11 +67,14 @@ fi
 set -o errexit -o pipefail -o noclobber -o nounset

 LOGIN_URL="$BASE_URL/api/v1/open/auth/login"
-SEARCH_URL="$BASE_URL/api/v1/sec/item/search"
+SEARCH_URL="$BASE_URL/api/v1/sec/item/searchWithTags"
 INSIGHT_URL="$BASE_URL/api/v1/sec/collective/insights"
 DETAIL_URL="$BASE_URL/api/v1/sec/item"
 ATTACH_URL="$BASE_URL/api/v1/sec/attachment"

+OVERWRITE_FILE=${OVERWRITE_FILE:-n}
+DROP_ITEM=${DROP_ITEM:-n}
+
 errout() {
    >&2 echo "$@"
 }
@ -133,6 +162,31 @@ fetchItem() {
    mcurl -XGET "$DETAIL_URL/$1"
 }

+downloadAttachment() {
+    attachId="$1"
+    errout " - Download '$attachName' ($attachId)"
+
+    if [ -f "$attachOut" ] && [ "$SKIP_FILE" == "y" ]; then
+        errout " - Skipping file '$attachOut' since it already exists"
+    else
+        if [ -f "$attachOut" ] && [ "$OVERWRITE_FILE" == "y" ]; then
+            errout " - Removing attachment file as requested: $attachOut"
+            rm -f "$attachOut"
+        fi
+
+        checksum1=$(curl --fail -s -I -H "X-Docspell-Auth: $auth_token" "$ATTACH_URL/$attachId/original" | \
+                        grep 'ETag' | cut -d' ' -f2 | jq -r)
+        curl --fail -s -o "$attachOut" -H "X-Docspell-Auth: $auth_token" "$ATTACH_URL/$attachId/original"
+        checksum2=$(sha256sum "$attachOut" | cut -d' ' -f1 | xargs)
+        if [ "$checksum1" == "$checksum2" ]; then
+            errout " - Checksum ok."
+        else
+            errout " - WARNING: Checksum mismatch! Server: $checksum1 Downloaded: $checksum2"
+            return 3
+        fi
+    fi
+}
+
 downloadItem() {
    checkLogin
    itemData=$(fetchItem "$1")
@ -142,14 +196,26 @@ downloadItem() {
    itemId=$(echo $itemData | jq -r '.id')
    out="$TARGET/$(date -d @$created +%Y-%m)/$itemId"

+    if [ -d "$out" ] && [ "$DROP_ITEM" == "y" ]; then
+        errout "Removing item folder as requested: $out"
+        rm -rf "$out"
+    fi
+
    mkdir -p "$out"
-    echo $itemData | jq > "$out/metadata.json"
+    if [ -f "$out/metadata.json" ] && [ "$SKIP_FILE" == "y" ]; then
+        errout " - Skipping file 'metadata.json' since it already exists"
+    else
+        if [ -f "$out/metadata.json" ] && [ "$OVERWRITE_FILE" == "y" ]; then
+            errout " - Removing metadata.json as requested"
+            rm -f "$out/metadata.json"
+        fi
+        echo $itemData | jq > "$out/metadata.json"
+    fi

    while read attachId attachName; do
-        errout " - download $attachName ($attachId)"
        attachOut="$out/$attachName"
        checkLogin
-        curl --fail -# -o "$attachOut" -H "X-Docspell-Auth: $auth_token" "$ATTACH_URL/$attachId"
+        downloadAttachment "$attachId"
    done < <(echo $itemData | jq -r '.sources[] | [.id,.name] | join(" ")')

 }
--- a/website/site/content/docs/faq/_index.md
+++ b/website/site/content/docs/faq/_index.md
@ -82,11 +82,9 @@ documentation, too.

 In order to move to a different tool, it is necessary to get the data
 out of Docspell in a machine readable/automatic way. Currently, there
-is no *easy way* for this. However, everything can be queried using a
-[HTTP/REST api](@/docs/api/_index.md) and so it is possible to get to
-all data with some scripting effort. There exists a script in the
-`tools/` folder that at least can go and download all files that have
-been uploaded to docspell.
+is a [export-files.sh](@/docs/tools/export-files.md) script provided
+(in the `tools/` folder) that can be used to download all your files
+and item metadata.

 My recommendation is to run periodic database backups and also store
 the binaries/docker images. This lets you re-create the current state
--- a/website/site/content/docs/tools/export-files.md
+++ b/website/site/content/docs/tools/export-files.md
@ -7,13 +7,54 @@ weight = 65
 # export-files.sh

 This script can be used to download all files from docspell that have
-been uploaded before.
+been uploaded before and the item metadata.
+
+It downloads the original files, those that have been uploaded and not
+the converted pdf files.
+
+The item's metadata are stored next to the files to provide more
+information about the item: corresponent, tags, dates, custom fields
+etc. This contains most of your user supplied data.
+
+This script is intended for having your data outside and independent
+of docspell. Another good idea for a backup strategy is to take
+database dumps *and* storing the releases of docspell next to this
+dump.
+
+Files are stored into the following folder structure (below the given
+target directory):
+
+```
+- yyyy-mm (item date)
+  - A3…XY (item id)
+    - somefile.pdf (attachments with name)
+    - metadata.json (json file with items metadata)
+```
+
+By default, files are not overwritten, it stops if existing files are
+encountered. This and some other things can be changed using
+environment variables:
+
+- `DS_USER` the account name for login, it is asked if not available
+- `DS_PASS` the password for login, it is asked if not available
+- `OVERWRITE_FILE=` if `y` then overwriting existing files is ok.
+  Default is `n`.
+- `SKIP_FILE=` if `y` then existing files are skipped (supersedes
+  `OVERWRITE_FILE`). Default is `n`.
+- `DROP_ITEM=` if `y` the item folder is removed before attempting to
+  download it. If this is set to `y` then the above options don't make
+  sense, since they operate on the files inside the item folder.
+  Default is `n`.
+
+Docspell sends the sha256 hash with each file via the ETag header.
+This is used to do a integrity check after downloading.
+

 # Requirements

 It is a bash script that additionally needs
-[curl](https://curl.haxx.se/) and
-[jq](https://stedolan.github.io/jq/).
+[curl](https://curl.haxx.se/) and [jq](https://stedolan.github.io/jq/)
+to be available.

 # Usage

@ -29,5 +70,139 @@ For example, if docspell is at `http://localhost:7880`:

 The script asks for your account name and password. It then logs in
 and goes through all items downloading the metadata as json and the
-attachments. It will fetch the original files (not the converted
-ones).
+attachments.
+
+
+# Example Run
+
+``` bash
+fish> env SKIP_FILE=y DS_USER=demo DS_PASS=test ./export-files.sh http://localhost:7880 /tmp/download
+Login to Docspell.
+Using url: http://localhost:7880
+
+Login successful
+Downloading 73 items…
+Get next items with offset=0, limit=100
+Get item 57Znskthf3g-X7RP1fxzE2U-dwr4vM6Yjnn-b7s1PoCznhz
+ - Download 'something.txt' (8HbeFornAUN-kBCyc8bHSVr-bnLBYDzgRQ7-peMZzyTzM2X)
+ - Checksum ok.
+Get item 94u5Pt39q6N-7vKu3LugoRj-zohGS4ie4jb-68bW5gXU6Jd
+ - Download 'letter-en.pdf' (6KNNmoyqpew-RAkdwEmQgBT-QDqdY97whZA-4k2rmbssdfQ)
+ - Checksum ok.
+Get item 7L9Fh53RVG4-vGSt2G2YUcY-cvpBKRXQgBn-omYpg6xQXyD
+ - Download 'mail.html' (A6yTYKrDc7y-xU3whmLB1kB-TGhEAVb12mo-RUw5u9PsYMo)
+ - Checksum ok.
+Get item DCn9UtWUtvF-2qjxB5PXGEG-vqRUUU7JUJH-zBBrmSeGYPe
+ - Download 'Invoice_7340224.pdf' (6FWdjxJh7yB-CCjY39p6uH9-uVLbmGfm25r-cw6RksrSx4n)
+ - Checksum ok.
+…
+```
+
+The resulting directory looks then like this:
+
+``` bash
+…
+├── 2020-08
+│   ├── 6t27gQQ4TfW-H4uAmkYyiSe-rBnerFE2v5F-9BdqbGEhMcv
+│   │   ├── 52241.pdf
+│   │   └── metadata.json
+│   └── 9qwT2GuwEvV-s9UuBQ4w7o9-uE8AdMc7PwL-GFDd62gduAm
+│       ├── DOC-20191223-155707.jpg
+│       └── metadata.json
+├── 2020-09
+│   ├── 2CM8C9VaVAT-sVJiKyUPCvR-Muqr2Cqvi6v-GXhRtg6eomA
+│   │   ├── letter with spaces.pdf
+│   │   └── metadata.json
+│   ├── 4sXpX2Sc9Ex-QX1M6GtjiXp-DApuDDzGQXR-7pg1QPW9pbs
+│   │   ├── analyse.org
+│   │   ├── 201703.docx
+│   │   ├── 11812_120719.pdf
+│   │   ├── letter-de.pdf
+│   │   ├── letter-en.pdf
+│   │   └── metadata.json
+│   ├── 5VhP5Torsy1-15pwJBeRjPi-es8BGnxhWn7-3pBQTJv3zPb
+│   │   └── metadata.json
+│   ├── 7ePWmK4xCNk-gmvnTDdFwG8-JcN5MDSUNPL-NTZZrho2Jc6
+│   │   ├── metadata.json
+│   │   └── Rechnung.pdf
+…
+```
+
+The `metadata.json` file contains all the item metadata. This may be
+useful when importing into other tools.
+
+``` json
+{
+  "id": "AWCNx7tJgUw-SdrNtRouNJB-FGs6Y2VP5bV-218sFN8mjjk",
+  "direction": "incoming",
+  "name": "Ruecksendung.pdf",
+  "source": "integration",
+  "state": "confirmed",
+  "created": 1606171810005,
+  "updated": 1606422917826,
+  "itemDate": null,
+  "corrOrg": null,
+  "corrPerson": null,
+  "concPerson": null,
+  "concEquipment": null,
+  "inReplyTo": null,
+  "folder": null,
+  "dueDate": null,
+  "notes": null,
+  "attachments": [
+    {
+      "id": "4aPmhrjfR9Z-AgknoW6yVoE-YkffioD2KXV-E6Vm6snH17Q",
+      "name": "Ruecksendung.converted.pdf",
+      "size": 57777,
+      "contentType": "application/pdf",
+      "converted": true
+    }
+  ],
+  "sources": [
+    {
+      "id": "4aPmhrjfR9Z-AgknoW6yVoE-YkffioD2KXV-E6Vm6snH17Q",
+      "name": "Ruecksendung.pdf",
+      "size": 65715,
+      "contentType": "application/pdf"
+    }
+  ],
+  "archives": [],
+  "tags": [
+    {
+      "id": "EQvJ6AHw19Y-Cdg3gF78zZk-BY2zFtNTwes-J95jpXpzhfw",
+      "name": "Hupe",
+      "category": "state",
+      "created": 1606427083171
+    },
+    {
+      "id": "4xyZoeeELdJ-tJ91GiRLinJ-7bdauy3U1jR-Bzr4VS96bGS",
+      "name": "Invoice",
+      "category": "doctype",
+      "created": 1594249709473
+    }
+  ],
+  "customfields": [
+    {
+      "id": "5tYmDHin3Kx-HomKkeEVtJN-v99oKxQ8ot6-yFVrEmMayoo",
+      "name": "amount",
+      "label": "EUR",
+      "ftype": "money",
+      "value": "151.55"
+    },
+    {
+      "id": "3jbwbep8rDs-hNJ9ePRE7gv-21nYMbUj3eb-mKRWAr4xSS2",
+      "name": "invoice-number",
+      "label": "Invoice-Nr",
+      "ftype": "text",
+      "value": "I454602"
+    },
+    {
+      "id": "AH4p4NUCa9Y-EUkH66wLzxE-Rf2wJPxTAYd-DeGDm4AT4Yg",
+      "name": "number",
+      "label": "Number",
+      "ftype": "numeric",
+      "value": "0.10"
+    }
+  ]
+}
+```