Initial commit: Klammertext source distribution

Curated source subset assembled by klammertext-dev's doc/make_dist.sh: the Klammermachine (mac), the Standard Klammer Set (sks), the commands (com), editor plugins and install guides (doc), a test subset (tst), and lib/bin placeholders. Builds with 'make -C com'. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-18 18:48:23 +02:00
commit 2ba7ceee7a
272 changed files with 27634 additions and 0 deletions
--- a/sks/image/pdf_image.py
+++ b/sks/image/pdf_image.py
@@ -0,0 +1,81 @@
+import re, subprocess, os
+
+def dimensions_from_prolog(filename):
+    mediabox_pat = re.compile(r"/MediaBox\s+\[(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\]", re.S)
+    width_pat = re.compile(r"/Width\s+(\d+)", re.S)
+    height_pat = re.compile(r"/Height\s+(\d+)", re.S)
+    width = None
+    height = None
+    with open(filename, mode="rb") as fp:
+        line = fp.readline().decode("ascii")
+        while line:
+            match = mediabox_pat.match(line)
+            if match:
+                x1, y1, x2, y2 = [int(e) for e in match.groups()]
+                width = x2 - x1
+                height = y2 - y1
+            else:
+                match = width_pat.match(line)
+                if match:
+                    width = int(match.group(1))
+                else:
+                    match = height_pat.match(line)
+                    if match:
+                        height = int(match.group(1))
+            if width and height:
+                break
+            line = fp.readline().decode("ascii")
+    return width, height
+
+
+def dimensions_from_pdfinfo(filename):
+    sp = subprocess.Popen(
+        ["/usr/bin/pdfinfo", filename], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+    out, err = sp.communicate()
+    out = out.decode("ascii")
+    width, height = None, None
+    if out:
+        pat = re.compile(r"Page size:\s+([\d.]+) x ([\d.]+) pts", re.S)
+        match = pat.search(out)
+        if match:
+            width, height = [int(round(float(e))) for e in match.groups()]
+    return width, height
+
+# Doesn't agree with pdfinfo; why?
+# from pdf2image import convert_from_path
+# def dimensions_from_pdf2image(filename):
+#     width, height = None, None
+#     if pdf2image_imported:
+#         img = convert_from_path(filename)[0]
+#         width, height = img.size
+#     return width, height
+
+
+def dimensions(filename):
+    width, height = None, None
+    try:
+        width, height = dimensions_from_prolog(filename)
+    except:
+        if width is None:
+            width, height = dimensions_from_pdfinfo(filename)        
+    if width is None:
+        raise Exception(f'Could not determine the width and height of "{filename}"')        
+    return width, height
+
+
+def convert(pdf_filename, image_filename):
+    if image_filename.endswith(".jpg"):
+        arg1 = "-jpeg"
+    elif image_filename.endswith(".png"):
+        arg1 = "-png"
+    else:
+        raise Exception(f'PDF file "{pdf_filename}" can only be converted to PNG or JPEG')
+    arg2 = "-singlefile"
+    command = "/usr/bin/pdftoppm"
+    basename = os.path.splitext(image_filename)[0]
+    sp = subprocess.Popen(
+        [command, arg1, arg2, pdf_filename, basename],
+        stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+    out, err = sp.communicate()
+    if err:
+        raise Exception(f'Error creating image file from "{pdf_filename}": {err}')